penetration-test-planner
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it is designed to ingest user-supplied security data and execute actions based on that data.
- Ingestion points: Processes user requests concerning penetration test patterns and configurations in SKILL.md.
- Boundary markers: Absent; the skill lacks specific delimiters or instructions to ignore instructions embedded within processed data.
- Capability inventory: Access to Bash, Write, Edit, and Read tools (defined in SKILL.md frontmatter).
- Sanitization: Absent; the instructions do not specify validation or sanitization procedures for user-provided data before interpolation into commands or generated code.
- [NO_CODE]: The skill consists only of markdown instructions and frontmatter configuration without any accompanying scripts or executable code files.
Audit Metadata