webapp-review
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local source code and external web application responses which can contain hidden instructions. 1. Ingestion points: SKILL.md (Workflow steps 2 and 5) describes inspecting local source code and capturing outputs from web security tools. 2. Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the processed data. 3. Capability inventory: The skill utilizes subprocess execution for tools such as curl, ffuf, nuclei, and sqlmap (Workflow step 5, Suggested Command Patterns). 4. Sanitization: There is no evidence of input validation or escaping for the data retrieved from external sources before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill is designed to autonomously execute command-line tools based on user-provided targets. Evidence: SKILL.md (Execution Policy) states the agent should "run routine in-scope command batches autonomously" and lists specific tools like curl, ffuf, nuclei, and sqlmap.
Audit Metadata