writing-shape

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes raw material from an external markdown file which could contain instructions intended to influence the agent's behavior.
  • Ingestion points: SKILL.md (instructions to read the input 'pile' file).
  • Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions embedded in the raw material.
  • Capability inventory: The skill has the ability to read and write files on the local filesystem.
  • Sanitization: No sanitization or filtering of the input content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 09:23 PM
Security Audit — agent-trust-hub — writing-shape