search-first
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's workflow involves fetching data from external, untrusted sources such as npm, PyPI, and GitHub to determine whether to 'Adopt', 'Extend', or 'Build' a solution. This exposes the agent to indirect prompt injection if the external content contains malicious instructions intended to influence the agent's behavior during the implementation phase.
- Ingestion points: External research data from npm/PyPI registries and GitHub repositories (SKILL.md).
- Boundary markers: None specified for the subagent's output or the retrieved content.
- Capability inventory: The agent is encouraged to install packages (npm install) and integrate code based on findings (SKILL.md).
- Sanitization: No explicit verification or sanitization steps are defined for the researched content before adoption.
Audit Metadata