internal-recon
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze data from the internal network, creating a surface for indirect injection attacks.
- Ingestion points: Networking data sources including ARP tables, DNS records, and service banners (SKILL.md, references/network-mapping.md).
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to mitigate the risk of instructions embedded within scanned network data.
- Capability inventory: The skill directs the agent to execute shell-based tools such as fscan, nmap, and httpx, which can be influenced by malicious network inputs (SKILL.md).
- Sanitization: No data sanitization or validation steps are included in the instructions.
- [COMMAND_EXECUTION]: The skill contains numerous command-line instructions for executing network reconnaissance tools.
- Evidence: Verbatim command templates for fscan, nmap, and native system commands (ip, route, net) are provided in SKILL.md and references/network-mapping.md.
Audit Metadata