documentation-verify

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill processes potentially untrusted repository data.\n
  • Ingestion points: The skill ingests documentation files and source code from the repository using git diff and directory scans as specified in SKILL.md.\n
  • Boundary markers: There are no specific delimiters or instructions provided to isolate the ingested file content from the agent's instructions.\n
  • Capability inventory: The skill directs the agent to execute shell-based search commands like grep, git grep, and ripgrep to find evidence for claims, which could be influenced by malicious content in those claims.\n
  • Sanitization: The skill lacks explicit sanitization or validation of the strings extracted from documentation before they are passed into search utilities.\n- [COMMAND_EXECUTION]: The skill requires the execution of system commands for its discovery and verification tasks.\n
  • Evidence: Use of git diff, grep, and ripgrep is integrated into the multi-stage workflow to identify documentation changes and verify them against the code as described in references/verification_procedures.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 08:56 PM