defining-pentest-scope
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from YAML files, creating a potential surface for indirect prompt injection.
- Ingestion points: The script
scripts/define_scope.pyreads in-scope and out-of-scope targets fromroe.yamland optional extension files. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potential instructions embedded within target names, URLs, or notes fields when the agent processes the generated reports.
- Capability inventory: The skill is authorized to use
Bash(python3:*)andReadtools, and it writes reports and target lists to the local file system. - Sanitization: While the script validates the syntax of network targets (IPs, CIDRs, hostnames), it does not sanitize descriptive fields or hostnames against strings that might influence the agent's behavior during subsequent analysis.
Audit Metadata