51mee-position-parse
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating untrusted job description text into a model prompt.
- Ingestion points: User-provided text is inserted into the
{职位描述文本}placeholder within the prompt template inSKILL.md. - Boundary markers: The skill attempts to isolate user input using markdown code blocks (
text ...), which is a weak delimiter that can be escaped by adversarial content. - Capability inventory: No dangerous tools, subprocess calls, network operations, or file-system writing capabilities were identified in the skill definition or referenced files.
- Sanitization: There is no evidence of input validation, filtering, or escaping logic to prevent malicious instructions within the job description from influencing the agent's behavior.
Audit Metadata