documentation-management

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes content from project files to maintain documentation accuracy.
  • Ingestion points: The agent reads project-level files using the Read and Grep tools to identify changes (SKILL.md, reference.md).
  • Boundary markers: There are no explicit delimiters or instructions defined to ignore potentially malicious embedded instructions within the source files.
  • Capability inventory: The skill employs Read, Edit, Write, and Grep tools, granting it the ability to modify files based on ingested content.
  • Sanitization: The instructions do not specify any validation or sanitization of input data before it is written to the documentation files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:52 AM