job-hunt
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses high-priority instructions to control agent behavior and suppress output during automated tasks (e.g., '最高优先级', '严禁输出任何文字').
- [PROMPT_INJECTION]: The skill processes job description data extracted from screenshots, which presents a surface for indirect prompt injection.
- Ingestion points: External job descriptions extracted via the fetcher skill in SKILL.md.
- Boundary markers: No specific delimiters or safety instructions are used to isolate job content from the agent's processing logic.
- Capability inventory: The agent has access to local file systems and shell execution (pwd, mkdir, rm).
- Sanitization: No explicit sanitization or filtering of the job description text is mentioned.
- [COMMAND_EXECUTION]: The skill executes local shell commands (pwd, mkdir, rm) for workspace management and data cleanup, which is consistent with its stated functionality.
Audit Metadata