code-documentation-doc-generate
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local codebase—including comments, docstrings, and configuration files—to produce documentation. This creates a surface for indirect prompt injection if the processed files contain malicious instructions designed to manipulate the agent.\n
- Ingestion points: Local source files and configurations are read as input for the documentation extraction logic described in
SKILL.mdandresources/implementation-playbook.md.\n - Boundary markers: There are no explicit delimiters or instructions to treat ingested code content as data distinct from instructions.\n
- Capability inventory: The skill uses file system read/write operations and shell command execution for build and validation tasks.\n
- Sanitization: Instructions explicitly warn against exposing secrets or sensitive data and caution against importing untrusted modules.\n- [COMMAND_EXECUTION]: The instructions direct the agent to run existing project commands, such as schema validators and documentation builders (
SKILL.md), to verify the output. This capability is expected for the skill's purpose but involves running arbitrary shell commands defined within the user's project.
Audit Metadata