gen-docs
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell commands such as
git log,git diff, andnodeto inspect the codebase and run a synchronization script. These are typical for repository maintenance tasks. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests data from external sources like commit messages and code changes.
- Ingestion points: Commit history (
git log), code changes (git diff), and changeset files (.changeset/*.md). - Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted data from the system prompt.
- Capability inventory: The agent has permissions to read/write local files and execute specific shell commands.
- Sanitization: No explicit sanitization or filtering is performed on the ingested git data.
Audit Metadata