mobile-pentest-plan
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source code from a directory path provided via the $ARGUMENTS parameter. This introduces an attack surface where malicious strings or comments embedded in the target codebase could attempt to influence the agent's behavior during the plan generation process. Ingestion points: Files accessed using the Read, Glob, and Grep tools (SKILL.md). Boundary markers: The instructions do not define clear delimiters or isolation protocols to prevent the agent from obeying instructions found within the code being analyzed. Capability inventory: Bash, Task, Write, WebSearch, Read, Glob, and Grep. Sanitization: No explicit content filtering or validation is described.
- [COMMAND_EXECUTION]: The instruction 'Analyze the codebase at: $ARGUMENTS' implies the interpolation of user-supplied input into the agent's operations. If the platform passes this string to shell-based tools such as Bash or Task without proper sanitization, it could be vulnerable to command injection if the path string contains shell metacharacters.
Audit Metadata