wiki-from-code

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes application source code to infer requirements and functionality, which introduces a vulnerability where malicious code comments or strings could manipulate the documentation generation process.
  • Ingestion points: The agent reads application source code files during the cataloging and diving phases to identify features and behaviors (SKILL.md).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the source code being analyzed.
  • Capability inventory: The skill has the capability to write markdown and YAML files across multiple directories (capabilities/, catalog/, mismatches/) and create new sub-folders (SKILL.md, references/layout.md).
  • Sanitization: The instructions do not specify any validation, filtering, or escaping of the content extracted from the source code before it is written to the wiki files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 01:08 AM
Security Audit — agent-trust-hub — wiki-from-code