nmap-parse
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external Nmap output files (XML, grepable, or normal formats). This creates a potential attack surface where instructions embedded in scan results could influence agent behavior.
- Ingestion points:
SKILL.md(Step 1) reads user-provided nmap output files. - Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard embedded commands in the data.
- Capability inventory:
SKILL.md(Step 6) involves filesystem writes and shell command execution (mkdir). - Sanitization: There is no evidence of sanitization or escaping of the parsed content.
- [COMMAND_EXECUTION]: The skill instructs the agent to perform basic shell operations.
- Evidence:
SKILL.md(Step 6) usesmkdir -p recon/to prepare the output directory for report storage.
Audit Metadata