recon-laundromats
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto perform network reconnaissance against target domains, checking for HTTP status codes and identifying CMS signatures. - [DATA_EXFILTRATION]: Instructions facilitate the discovery of sensitive information on target servers, such as customer PII in debug logs and exposed invoice files.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface when processing remote content:
- Ingestion points: Fetches untrusted data from target websites using
curl(SKILL.md). - Boundary markers: No delimiters are present to isolate remote data from the agent's instructions.
- Capability inventory: Includes the ability to execute network requests, file system interactions (via curl output redirection), and data parsing with
grepandjq. - Sanitization: The skill does not perform sanitization of the remote data before it is processed by shell utilities.
Audit Metadata