simplify-pass
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code, instructions, and test files as input. These are untrusted sources that could contain malicious instructions (e.g., hidden in comments) designed to override the agent's behavior or the behavior of delegated sub-agents.
- Ingestion points: The skill reads affected code, callers, project instructions, and existing tests in
SKILL.md. - Boundary markers: There are no explicit delimiters or specific instructions to ignore embedded natural language prompts within the code being analyzed.
- Capability inventory: The skill reads and writes files, delegates tasks to other agent instances, and executes local test commands.
- Sanitization: No sanitization or structural validation is performed on the ingested code or instructions before they are processed.
- [COMMAND_EXECUTION]: The instructions require the agent to execute project-specific test suites to establish baselines and verify changes. This is a standard capability for developer tools but constitutes execution of local code.
- Evidence:
SKILL.mdinstructs the agent to "Run a focused existing check before editing" and "Run the focused checks that cover the affected behavior."
Audit Metadata