pm-feedback

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user-provided feedback data (CSV, Excel, or text), which creates a surface for indirect prompt injection.
  • Ingestion points: Feedback data is ingested as primary input as described in the 'Inputs' and 'Step 1' sections of SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or warnings for the agent to ignore potential instructions embedded within the feedback.
  • Capability inventory: The skill's capabilities are focused on data analysis, clustering, and report generation; it does not request dangerous tools for network access or file system modification.
  • Sanitization: No evidence of input validation or sanitization exists to filter out malicious commands from the feedback corpus.
  • [NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable scripts or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 04:37 PM
Security Audit — agent-trust-hub — pm-feedback