hiring-by-role
Fail
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation in
references/interview-experts.mdincludes a link toworkrules.net. This domain is currently flagged as blacklisted by automated security scanners, posing a risk to users or agents that attempt to access the resource. - [COMMAND_EXECUTION]: The skill provides and instructs the agent to run a Python script (
scripts/check-output.py) to validate output. The script accepts file paths as command-line arguments and reads their contents. While the script's logic is benign (checking for specific headers), the provision of scripts that perform file I/O based on agent-controlled arguments increases the local attack surface. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection. 1. Ingestion points: User-provided role, company, and product details in
SKILL.mdtemplates. 2. Boundary markers: No delimiters or instructions are used to separate untrusted user data from agent instructions. 3. Capability inventory: The agent can execute local Python scripts and read files. 4. Sanitization: No input filtering or escaping is implemented for user-supplied strings.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- Contains 3 malicious URL(s) - DO NOT USE
Audit Metadata