resolving-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from repository history which could contain malicious instructions designed to exploit the agent's command execution capabilities. * Ingestion points: The instructions require the agent to read commit messages, pull request descriptions, and issue/ticket content from the project history (SKILL.md). * Boundary markers: The skill does not provide delimiters or specific instructions to the agent to treat this external content as data only, leaving it susceptible to instruction overrides. * Capability inventory: The agent is instructed to discover and execute project-specific automated checks, which involves running arbitrary shell commands like test suites or build scripts (SKILL.md). * Sanitization: There is no evidence of sanitization or character escaping for the content retrieved from the external git metadata before it is processed.
Audit Metadata