skills/gdewitte/agentic/plan/Gen Agent Trust Hub

plan

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data from user arguments and specification files to generate implementation plans. While this creates a surface for indirect prompt injection, it is assessed as safe because it is central to the skill's primary purpose and does not possess high-risk capabilities.
  • Ingestion points: Reads input from $ARGUMENTS and files matching the pattern docs/specs/<feature-slug>-spec.md.
  • Boundary markers: No specific delimiters or boundary instructions are present to distinguish untrusted data from the system prompt.
  • Capability inventory: The skill is capable of reading source files and writing implementation plans to the docs/plans/ directory.
  • Sanitization: The skill does not perform explicit validation, filtering, or escaping of the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 02:44 PM
Security Audit — agent-trust-hub — plan