review
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted test files which provides a surface for instructions embedded in code comments or strings to influence the agent's review logic or file-writing actions.
- Ingestion points: The skill reads
playwright.config.ts,*.spec.ts, and*.spec.jsfiles to gather context and identify anti-patterns as described in SKILL.md. - Boundary markers: The instructions do not define explicit delimiters (like XML tags or triple quotes) for the code content, nor do they include specific directives for the agent to ignore any natural language instructions found within the code.
- Capability inventory: The skill possesses the capability to write to the file system using the
Edittool to apply suggested fixes, which could be exploited if the agent is influenced by malicious instructions in the code it reviews. - Sanitization: Although the skill includes a human-in-the-loop checkpoint by asking the user to confirm fixes, it does not implement automated sanitization or validation of the ingested code content to prevent prompt injection at the analysis stage.
Audit Metadata