pm-initiate-project-context

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted repository data to populate context files that guide future agent actions.
  • Ingestion points: Step 3 (Gather information) explicitly instructs the agent to read repository artifacts, documentation, and notes to auto-draft the project context.
  • Boundary markers: The instructions do not require the use of delimiters or 'ignore' warnings for the content being drafted from external repository files.
  • Capability inventory: The skill writes to the .agents/ directory, creating a persistent 'source of truth' that is then read by other PM-related skills.
  • Sanitization: No specific sanitization, filtering, or validation of the content retrieved from repository artifacts is defined before it is saved into the context documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 07:03 PM
Security Audit — agent-trust-hub — pm-initiate-project-context