adev-writing-guide

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown documentation and instructions, with no executable scripts or code provided.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to be used when the agent is editing or reviewing documentation files in the adev/ repository. This creates a surface for indirect prompt injection if those files contain instructions from untrusted sources.
  • Ingestion points: Markdown files within the adev/src/content directory.
  • Boundary markers: The skill does not provide instructions for using delimiters or boundary markers to distinguish documentation content from instructions.
  • Capability inventory: The skill is active while the agent performs file reading and writing tasks related to documentation.
  • Sanitization: No sanitization or validation protocols are defined for the external content being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:19 PM
Security Audit — agent-trust-hub — adev-writing-guide