ape-plan-project

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (PRDs, engineering design docs, and rough notes) to generate planning documents, which creates a potential surface for indirect prompt injection where malicious instructions in the input could influence agent behavior.
  • Ingestion points: User-provided specifications, engineering design documents, and rough notes described in the Input section of SKILL.md.
  • Boundary markers: None. The instructions do not mandate the use of delimiters or specific framing to isolate untrusted input content.
  • Capability inventory: The skill requires file system read access to verify the current codebase and file system write access to generate and save design documents to disk.
  • Sanitization: No input sanitization, content filtering, or validation mechanisms are specified for the processed documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 11:56 AM
Security Audit — agent-trust-hub — ape-plan-project