unblocked-context-search-prs
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'unblocked' CLI tool to perform semantic searches of PR data. This execution is the intended method for retrieving context from external repositories.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of PR metadata and discussion history from external platforms including GitHub, GitLab, and Bitbucket. This activity is required for the tool's core functionality.
- [PROMPT_INJECTION]: The skill processes untrusted PR descriptions and comments, creating an indirect prompt injection surface. Ingestion points: External PR data enters the agent context through the 'context_search_prs' CLI command output as described in SKILL.md. Boundary markers: Explicit delimiters for the retrieved PR content are absent, though the instructions recommend the agent verify findings against local files. Capability inventory: The skill employs shell command execution for the 'unblocked' utility. Sanitization: No specific sanitization or filtering logic is specified for the external content retrieved by the tool.
Audit Metadata