greenhouse
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest and process external data from Greenhouse, such as applicant names, resumes, and application details, creating a surface for potential indirect prompt injection attacks.\n
- Ingestion points: Candidate and application data retrieved via the
applicantsandapplicationsresource endpoints (File: SKILL.md).\n - Boundary markers: The skill does not provide specific instructions for using delimiters or data isolation techniques when handling external content.\n
- Capability inventory: The skill documents capabilities to perform network-based write operations, such as creating new applicants or updating application stages in the Greenhouse ATS (File: SKILL.md).\n
- Sanitization: There is no documentation regarding the validation or sanitization of data retrieved from the Greenhouse API.\n- [NO_CODE]: This skill consists of documentation and implementation examples; it does not distribute standalone scripts, binaries, or automated installation routines.
Audit Metadata