Alpha Preview: Fidensa is currently in early testing. Scores are for demonstration purposes and are not considered final or reliable.
voltcc-subagents
A comprehensive Claude Code plugin providing 100+ specialized sub-agents organized across 10 categories for development, infrastructure, quality assurance, data analysis, and business operations.
67
/ 100 · Grade D
D = 60–69
“I need to access a comprehensive suite of specialized coding and development sub-agents that can handle diverse tasks across development, infrastructure, quality control, and business analysis without switching between multiple tools.”
voltcc-subagents earned Verified status with a trust score of 67/100 (Grade D). Adversarial testing produced 7 findings (7 high). Supply chain is clean — 1 components with no known vulnerabilities. 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 install-agents.sh script accepts user input for category and agent selection, then uses this input in file paths and curl commands without proper validation. User input is directly interpolated into shell commands and file operations.
The script uses user-selected category names and agent filenames directly in file system operations and curl commands. Malicious input like '../../../etc/passwd' or '; rm -rf /' could potentially escape intended directories or inject additional commands.
The install-agents.sh script uses curl with flags that bypass safety checks and confirmation dialogs. The script uses 'curl -sS' (silent mode with some error output) and 'curl -sf' (silent mode with fail-fast) which suppress normal user feedback. Additionally, the script automatically proceeds with file operations without explicit user confirmation in several places, and uses 'set -e' which can mask error conditions.
Both install-agents.sh and the subagent-catalog configuration scripts write to global system locations outside the project scope. The installer creates and modifies directories in ~/.claude/agents/ (global installation) and ~/.claude/cache/ (cache directory). These operations affect system-wide configuration and persist beyond the current project.
The install-agents.sh script contains persistent configuration that affects Claude's behavior across all future sessions. The script installs agents globally to ~/.claude/agents/ or locally to .claude/agents/, and these agents contain behavioral instructions that will persist beyond the current task execution.
The installation script creates persistent agent files in user directories (~/.claude/agents/ and .claude/agents/) that will be automatically loaded by Claude in future sessions. This creates persistent behavioral modifications without explicit per-session consent.
The plugin system claims authority over Claude's agent loading mechanism and behavioral modification through file system manipulation. While the stated purpose is agent management, the implementation creates system-level persistence that could affect unrelated tasks.
Methodology v1.0 · 6 categories · ~55 attack patterns
Supply Chain
SBOM analysis and vulnerability assessment
Components
1
Direct deps
0
Transitive deps
1
Total vulns
0
Format: CycloneDX 1.5 · Generated: Apr 1, 2026
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: Apr 1, 2026 · Status: baseline
Component Inventory
141 components composing this plugin
agents
139
scripts
2
agents (139)
scripts (2)
Interface
Aggregated instruction summary
Scope & Permissions
What this capability can and cannot access — derived from pipeline analysis
no
no
yes
no
yes
no
Badge & Integration
Embed certification status in your README, docs, or CI pipeline
Certification Notes
Provenance observations from the pipeline
Publisher "VoltAgent" 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
Package description appears to be boilerplate or template text
Signed Artifact
Certification provenance and verification metadata
The original instruction file with a certification footer appended. Replace the source file in your project so AI agents see the trust score, verification link, and SOP.
ES256-signed JWS artifact for programmatic verification. Use with the Fidensa MCP server or GitHub Action to validate integrity.
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.