infographic-outline-creator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's architecture presents a vulnerability surface for indirect prompt injection attacks.\n
- Ingestion points: Workspace files processed via the
Read,Edit, andGreptools.\n - Boundary markers: There are no explicit instructions for the agent to distinguish between its own logic and potentially malicious instructions embedded in data files.\n
- Capability inventory: The skill is permitted to use
Bash(cmd:*), which allows for arbitrary command execution, and file system modification tools (Write,Edit).\n - Sanitization: No evidence of input validation or sanitization for file contents before they are interpreted or used in subsequent operations.\n- [NO_CODE]: The skill consists exclusively of markdown instructions and metadata, with no accompanying scripts or executable files provided in the skill package.
Audit Metadata