nemoclaw-contributor-update-docs
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from external sources such as git commit messages and pull request contexts.
- Ingestion points: The instructions in
SKILL.mdrequire the agent to read commit history, PR context, and source files to identify behavioral changes. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the ingested data as untrusted or to ignore instructions embedded within those data sources.
- Capability inventory: The skill has the capability to write to the file system (specifically
docs/**) and execute build scripts. - Sanitization: No sanitization or filtering logic is defined for the external text before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute project-specific shell commands for documentation validation.
- Evidence: The skill invokes
npm run docsto check the generated documentation and links.
Audit Metadata