skills/oabdelmaksoud/agention/ecc-claude-ra-qm-team-quality-manager-qms-iso13485/Gen Agent Trust Hub
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