claude-simone
A project management framework that provides structured workflows, prompts, and tooling for AI-assisted software development using markdown configuration files.
71
/ 100 · Grade D
D = 60–69
“I need to manage AI-assisted development projects with structured workflows, automated task management, and organized code review processes.”
claude-simone earned Verified status with a trust score of 71/100 (Grade D). Adversarial testing produced 7 findings (6 high, 1 medium). Security scan flagged 0 findings. Tier is Verified rather than Certified due to unmitigated findings above severity thresholds.
Trust Score Breakdown
Eight weighted signals composing the aggregate trust score
Scheme v2.0 · Weights provisional · Consumer confirmations and uptime use pipeline-derived baselines.
Findings
Security scan results, adversarial testing, and pipeline review
Security Scan — Cisco Skill Scanner
Adversarial Testing — 6 categories, 7 findings
The version-manager.js script uses execSync to execute git commands with user-provided input that is not properly sanitized. The 'tag' and 'migrate-tags' commands construct shell commands using string interpolation with user-controlled values like component.version and tag names, creating command injection vulnerabilities.
The install-mcp.js script constructs curl commands using string interpolation with template names that could potentially be controlled or influenced by external factors. While the template names appear to be hardcoded in this instance, the pattern of using execAsync with string interpolation for shell commands creates a potential injection surface.
The skill's version-manager.js script uses execSync to execute git commands and other shell operations, but the skill only declares 'log_activity' and 'filesystem_access' as dependencies. The script executes git commands like 'git tag -l', 'git tag -a', and 'git rev-list' which would require shell/command execution capabilities that are not declared.
The skill contains instructions that execute system-level git commands and curl operations that operate beyond the project scope. The install-mcp.js file executes 'git --version' checks and downloads files from external URLs using curl. The version-manager.js creates git tags and accesses git repository state, which are system-level operations that modify version control state beyond just file operations.
The version-manager.js script contains conditional logic that references git tags and file system state that users wouldn't necessarily be aware of. The script checks for existing git tags, reads package.json files, and makes decisions based on file existence - all system state that could vary unexpectedly.
The skill executes git commands and npm operations through execSync without declaring these as dependencies. The version-manager.js file uses execSync to run 'git tag', 'git rev-list', and other git commands, while install-mcp.js uses execAsync to run 'curl' and 'git --version'. These represent undeclared system dependencies that could be exploited if the underlying commands are compromised or if the skill is run in an environment where these tools behave unexpectedly.
The install-mcp.js file downloads template files directly from GitHub raw URLs using curl without integrity verification. This bypasses package registry security checks and could be exploited if the GitHub repository is compromised or if there's a man-in-the-middle attack. The downloaded content is written directly to the filesystem without validation.
Methodology v1.0 · 6 categories · ~55 attack patterns
Behavioral Fingerprint
Runtime performance baseline for drift detection
Samples
8
Error rate
0.0%
Peak memory
— MB
Avg CPU
—%
Response time distribution
Output size distribution
Fingerprint v1.0 · Baseline: Mar 29, 2026 · Status: baseline
Interface
Skill triggers and instruction summary
Activation
This skill activates when working with the Claude Simone repository, which is a meta-repository for developing a task and work management system for Claude Code.
This skill handles navigation and understanding of the Simone repository structure, including legacy, hello-simone, and mcp-server components.
Does
Use the log_activity tool to record activities after every relevant project activity
Recognize the meta-repository nature where the repo uses Simone to manage its own development
Distinguish between the stable legacy system and the early-development MCP server
Use the legacy system for actual project management tasks
Report any dependencies found outside the designated directories
Does not
Use the MCP server for production project management
Ignore the activity logging requirement
Treat all components as equally mature or ready for use
Scope & Permissions
What this capability can and cannot access — derived from pipeline analysis
no
no
no
no
yes
no
Known Failure Modes
Documented edge cases and recovery behaviors
when when dependencies are found outside designated directories
then the agent reports this to the user
when when activity logging is skipped
then the agent fails to track development progress properly
Badge & Integration
Embed certification status in your README, docs, or CI pipeline
Certification Notes
Provenance observations from the pipeline
Publisher "Helmi" is not verified — first certification from this publisher
No SECURITY.md or SECURITY.txt file found — no published vulnerability reporting process
Single contributor — no peer review evidence in commit history
Signed Artifact
Certification provenance and verification metadata
Pipeline Artifacts
Raw data files from this certification run — downloadable for independent verification
contract.json
Full unsigned contract
stage1-ingest.json
Ingest stage output
stage2a-sbom.json
SBOM generation results
stage2a-vulns.json
Vulnerability scan results
stage2b-security.json
Security scan results
stage3a-functional.json
Functional test results
stage3b-adversarial.json
Adversarial test results
stage3c-fingerprint.json
Behavioral fingerprint
stage4-certify.json
Certification decision + trust score
stage3a-measurements.json
Raw functional test measurements
stage3b-measurements.json
Raw adversarial test measurements
run-log.json
Pipeline execution log
Not all files may be present for every certification.