docstring-generator

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code via the full_text input to generate documentation. This represents an attack surface where malicious instructions hidden in comments within the source code could influence the agent's behavior during the documentation process.
  • Ingestion points: The full_text input parameter in SKILL.md receives the entire content of a source file.
  • Boundary markers: The instructions do not define clear delimiters or warnings to ignore instructions embedded within the processed code.
  • Capability inventory: The skill itself is restricted to returning text strings (updated_text, summary) and does not possess network, file system, or command execution capabilities.
  • Sanitization: There is no explicit sanitization or filtering of the input code to prevent embedded instructions from affecting the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 03:02 PM
Security Audit — agent-trust-hub — docstring-generator