run-smoke-tests
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious code, obfuscated content, or unauthorized exfiltration patterns were detected. The skill is designed with defensive prompting to ensure the agent remains within authorized test boundaries.
- [COMMAND_EXECUTION]: The skill facilitates the execution of build, launch, and CLI commands found within the target repository. It manages security risks by requiring the agent to identify authoritative sources and environment boundaries before starting any process.
- [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface (Category 8) as it ingests repository metadata and user-provided journey files. This is mitigated by explicit instructions: 1) Ingestion points: Reads local READMEs and manifests (SKILL.md Step 1); 2) Capability inventory: Executes commands and network requests derived from the repo; 3) Boundary markers: Requires validation of the journey contract and preflight health checks (Step 2 and 3); 4) Sanitization: Forbids guessing commands, bypassing human checkpoints, or handling raw secrets (Step 4).
Audit Metadata