absolute-documentations
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection as it ingests untrusted data from the repository being documented. Maliciously crafted documentation or code comments could influence the agent's output or actions.
- Ingestion points: The 'Recon' step in SKILL.md instructs the agent to read existing documentation and the codebase surface.
- Boundary markers: There are no specified delimiters or instructions to ignore embedded commands within the ingested files.
- Capability inventory: The skill allows the agent to write new documentation files and update existing ones (SKILL.md).
- Sanitization: No validation or sanitization of codebase content is mentioned before it is processed or written back to files.
- [COMMAND_EXECUTION]: The skill's 'Accuracy Protocol' instructs the agent to execute code snippets found in the codebase to verify their correctness. This creates a risk of arbitrary command execution if the snippets in the repository are malicious.
- Evidence: SKILL.md states: "If a snippet is runnable in this environment, run it."
Audit Metadata