write-documentation

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to verify code examples and run formatting or linting tools as defined by the project.
  • Evidence: SKILL.md includes instructions to "Run every example" (Rule 3) and "Run the project's format and doc-lint commands" (Rule 8).
  • Evidence: references/task-template.md notes that commands are resolved from the repository's AGENTS.md file.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes and incorporates content from potentially untrusted source code and documentation files.
  • Ingestion points: Source code and documentation files read during the documentation task (SKILL.md, Rule 7; references/task-template.md, Source material).
  • Boundary markers: No specific delimiters or safety instructions are used to isolate ingested content from the agent's instructions.
  • Capability inventory: The skill utilizes subprocess execution for verifying code examples and running project tools.
  • Sanitization: No validation or filtering is applied to the ingested content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 02:49 PM
Security Audit — agent-trust-hub — write-documentation