documentation-writer

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external content via the [PASTE CODE OR SPECIFICATION] variable, which could potentially contain hidden instructions designed to hijack the model's behavior.
  • Ingestion points: The input is captured in SKILL.md via the [PASTE CODE OR SPECIFICATION] placeholder.
  • Boundary markers: The template uses <code_or_spec> tags to delineate user-provided data from instructions.
  • Capability inventory: The skill is primarily a text-to-text prompt template and does not appear to execute shell commands, perform network operations, or write to the file system.
  • Sanitization: No specific input sanitization or validation logic is defined to check the content of the pasted code or spec.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 11:24 PM
Security Audit — agent-trust-hub — documentation-writer