hiring-panel
Fail
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: CRITICALMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill includes the URL "https://chen.media" in the metadata "homepage" field and appends it as a signature to all generated output files (PANEL.md and RESUME-IMPROVED.md). This URL has been flagged as malicious by automated scanners (URL:Blacklist), posing a risk to users who may interact with the domain.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted resume data from external files or user input and uses it to generate new documents and agent responses, creating an attack surface for indirect prompt injection.\n
- Ingestion points: The skill reads resume content from user-provided file paths (including PDFs) or pasted text via the "/hiring-panel" command in SKILL.md.\n
- Boundary markers: No explicit delimiters or instructions are used to isolate the untrusted resume content or warn sub-agents to ignore embedded instructions.\n
- Capability inventory: The skill possesses file system capabilities, specifically the ability to create new directories and write Markdown files to the workspace.\n
- Sanitization: There is no evidence of sanitization, filtering, or validation of the resume content before it is processed by the hiring panel sub-agents.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata