pmo-retrospective

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of external project data.
  • Ingestion points: Gate 2 (Data Collection) and Gate 3 (Reflection) in SKILL.md involve gathering metrics, variance explanations, and session data from external project contexts.
  • Boundary markers: None identified. The instructions do not define delimiters or provide 'ignore embedded instructions' warnings for the data being gathered.
  • Capability inventory: The skill performs file-write operations to the docs/pmo/ directory for each gate output.
  • Sanitization: There is no mention of escaping, validation, or filtering of the incoming project data before it is incorporated into the retrospective reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 07:56 AM