tech-docs-generator
Warn
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: MEDIUMINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs deep analysis of a codebase (SKILL.md), which serves as a source of untrusted data. Instructions or malicious content embedded in source code files, comments, or documentation could influence the doc-generator subagents.
- Ingestion points: Codebase analysis in Phase 1 (SKILL.md).
- Boundary markers: None specified to prevent the agent from following instructions embedded in the code.
- Capability inventory: File system write (docs/), git commit, and shell command execution.
- Sanitization: No explicit sanitization or filtering of codebase content is mentioned.
- [COMMAND_EXECUTION]: In the Verification Gate section, the skill instructs the agent to run any documented commands to confirm they work. This creates a vulnerability where malicious commands embedded in the project could be automatically executed by the agent during the documentation verification process.
- [DATA_EXFILTRATION]: The skill is instructed to capture configuration details including environment variables and configuration files. This may result in the unintentional exposure of sensitive environment variables or credentials found in .env files within the generated documentation files.
Audit Metadata