combine-docs
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the documentation files it processes. 1. Ingestion points: The skill reads project documentation including .md, .mdx, .txt, and .rtf files using the Read tool as specified in SKILL.md Step 2. 2. Boundary markers: There are no instructions to use delimiters or specific safety boundaries when interpolating file content into the agent's context. 3. Capability inventory: The skill possesses Write, Edit, and Bash (git mv) capabilities as specified in SKILL.md Step 4. 4. Sanitization: The skill does not sanitize or filter the content of the documents it reads. This risk is mitigated by a human-in-the-loop approval requirement in Step 3.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git commands, specifically 'git mv', for archiving or moving files. These commands are restricted to documentation management and are only executed after a consolidation plan is approved by the user.
Audit Metadata