recon-scope-triage
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a bash code snippet in
SKILL.mdthat usescurlto fetch content from remote URLs (e.g.,https://host.target.com/.env) andcmpto compare local temporary files. While intended for verification purposes during a security engagement, these commands are executed based on hostnames provided in untrusted reconnaissance datasets. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources such as ASM reports, recon exports, and breach corpora. This presents an attack surface where malicious data could influence agent behavior, although the skill's primary purpose is to act as a sanitization and verification layer for such data.
- Ingestion points: Reconnaissance datasets, ASM reports, repo lists, and bucket lists processed as described in
SKILL.md. - Boundary markers: None identified in the prompt templates.
- Capability inventory: Shell execution (
curl,cmp) and local file system access (/tmp) defined inSKILL.md. - Sanitization: The skill serves as a manual or logic-based sanitization process to identify and discard false positives, but it does not implement automated sanitization of the input data itself.
Audit Metadata