web-vuln-scan
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external web targets during scanning, which creates a surface for indirect prompt injection.
- Ingestion points: Tool outputs from network scanners in
SKILL.md(curl, httpx, nuclei, spray, ffuf) andreferences/scan-methodology.md(wfuzz) which process HTTP responses from potentially untrusted web servers. - Boundary markers: Absent; the methodology does not specify delimiters or instructions for the agent to differentiate between tool metadata and instructions embedded in the target server's response.
- Capability inventory: The skill makes use of powerful CLI tools across
SKILL.mdandreferences/scan-methodology.mdfor network interaction and reading local dictionary files. - Sanitization: Absent; the skill does not define methods for sanitizing external web content before it enters the agent's context.
- [COMMAND_EXECUTION]: The skill provides numerous shell commands for executing reconnaissance and vulnerability scanning tools including curl, httpx, nuclei, ffuf, and wfuzz to perform technical stack identification and security testing.
Audit Metadata