ecc-claude-ra-qm-team-quality-manager-qms-iso13485

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting guidance from external reference paths to determine execution steps. Ingestion points: The skill reads a reference path from references/upstream-path.txt which points to upstream-import/claude-skills/references/ra-qm-team/quality-manager-qms-iso13485. Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are defined in the workflow. Capability inventory: The agent is instructed to translate guidance into tool-backed steps and execute them incrementally. Sanitization: There is no specification for sanitizing or validating the content of the referenced files before processing.
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were found. The skill's behavior is consistent with its stated purpose of providing specialized domain guidance.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 06:05 PM
Security Audit — agent-trust-hub — ecc-claude-ra-qm-team-quality-manager-qms-iso13485