refactor
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted source code and possesses the capability to modify files and execute shell commands.
- Ingestion points: Reads source code from the files, directories, or modules specified in the
scopeinput. - Boundary markers: None; the skill does not define delimiters or instructions to isolate the source code content from the agent's instructions.
- Capability inventory: The agent is instructed to modify files (Procedure step 5) and execute test/lint commands (Procedure steps 2 and 6) using the shell.
- Sanitization: There is no evidence of sanitization or validation of the ingested code content before it is processed by the agent.
Audit Metadata