js-docs-sync
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell commands including
find,git diff, andpnpm run -r buildto identify project structure, track changes, and verify the integrity of the build. These operations are standard for development automation. - [INDIRECT_PROMPT_INJECTION]: The skill operates on project files such as source code and documentation which are external inputs. A malicious actor could attempt to embed instructions within these files to influence the agent's behavior during the synchronization process.
- Ingestion points: Reads from
js/packages/*/src/andjs/packages/*/docs/. - Boundary markers: None defined for untrusted project content.
- Capability inventory: The agent can read/write files and execute shell commands within the workspace.
- Sanitization: No specific filtering or escaping is applied to the content read from files before it is used to update documentation.
Audit Metadata