pmf-context

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection related to its processing of local project files.\n
  • Ingestion points: The skill reads markdown files located in the 'pmf/' directory, including 'icp.md', 'value-prop.md', 'aha-moments.md', and 'validation-plan.md', to display status summaries.\n
  • Boundary markers: There are no specific instructions or delimiters used to ensure that content within these files is not interpreted as instructions by the agent.\n
  • Capability inventory: The skill has access to 'Read', 'Write', 'Glob', and 'AskUserQuestion' tools across the project directory.\n
  • Sanitization: No mechanisms for escaping, validating, or sanitizing the ingested file content are specified in the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 06:21 AM