Skills
Navigate
skills/kmshihab7878/claude-code-setup/quality-manager-qmr/Gen Agent Trust Hub

quality-manager-qmr

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data including customer feedback, audit results, and regulatory updates, which represents a potential surface for indirect prompt injection attacks.
  • Ingestion points: references/qmr-operating-reference.md defines workflows for collecting customer feedback, audit results, and changes affecting the QMS.
  • Boundary markers: The instructions do not define specific delimiters or "ignore instructions" tags for processing these external data sources.
  • Capability inventory: The skill references execution of a local script scripts/management_review_tracker.py for metric tracking.
  • Sanitization: The provided files do not mention sanitization or validation of the ingested text data.
  • [COMMAND_EXECUTION]: The skill references a local Python script intended to track management review metrics and actions.
  • Evidence: references/qmr-operating-reference.md contains documentation for running scripts/management_review_tracker.py using the command python management_review_tracker.py --help.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 05:05 PM