job-interview-prep
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which constitutes a potential attack surface.
- Ingestion points: Resume and Job posting inputs in Step 1 (SKILL.md).
- Boundary markers: Absent; there are no specific instructions or delimiters provided to distinguish between user data and potential embedded instructions.
- Capability inventory: The skill lacks any access to dangerous tools or capabilities, such as network access, file system writes, or shell command execution. Its output is limited to text generation for interview preparation.
- Sanitization: Absent; the skill does not specify any sanitization or filtering logic for the input documents.
- [SAFE]: The skill does not contain any malicious code, obfuscation, hardcoded credentials, or persistence mechanisms. It is purely instructional and intended for text analysis and role-playing scenarios.
Audit Metadata