run-tests
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and executes code from external pull requests, which presents a vulnerability surface for indirect prompt injection or malicious code execution.
- Ingestion points: The skill operates on the PR head branch code as specified in SKILL.md.
- Boundary markers: None are provided to explicitly delimit external code from the agent's control instructions.
- Capability inventory: The skill has the capability to execute shell commands via pnpm and vitest (SKILL.md).
- Sanitization: The skill incorporates security best practices by requiring the use of infisical for secret management and explicitly forbidding the printing of sensitive values.
- [COMMAND_EXECUTION]: The skill uses pnpm and vitest to build internal workspace packages and run automated tests.
Audit Metadata