email-finder
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to use standard shell utilities such as
git,curl, andgrepto fetch commit logs, query search engines, and call verification APIs. These commands are integral to the stated purpose of the skill. - [EXTERNAL_DOWNLOADS]: The workflow relies on data retrieval from reputable domains including
github.com,api.github.com, and well-known lead generation services such as Apollo, Hunter, and Crustdata. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by processing untrusted user inputs (GitHub handles, LinkedIn URLs, names) and incorporating them into shell commands. Ingestion points: User-provided handles, URLs, and names via SKILL.md. Boundary markers: Absent in the suggested commands. Capability inventory: Use of
curlandgitfor network-based data retrieval. Sanitization: Absent; the skill does not explicitly instruct the agent to escape or validate user inputs before command interpolation.
Audit Metadata