quality-manager-qmr
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, specifically customer feedback and audit results, which could contain malicious instructions designed to influence the agent's behavior during report generation. \n
- Ingestion points: Data enters the context via the 'Management Review Workflow' in
SKILL.mdand the JSON data file processed byscripts/management_review_tracker.py.\n - Boundary markers: Absent. There are no explicit instructions to the agent to treat external feedback as data rather than instructions, nor are there delimiters defined for these inputs.\n
- Capability inventory: The skill includes file-read capabilities and local metric processing via
scripts/management_review_tracker.py. It does not possess network access, arbitrary command execution, or sensitive file system write permissions.\n - Sanitization: Absent. The skill does not describe any methods for sanitizing or validating the strings received from customer feedback or audit reports before they are processed or summarized.
Audit Metadata