studio-develop-cro-audit
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the user's repository to generate an audit report, creating a surface for indirect prompt injection.
- Ingestion points: The skill scans various source files including
package.json, framework configuration files, and component files (e.g.,src/components/*.tsx) across the entire repository. - Boundary markers: There are no instructions to the agent to treat content within the scanned files as untrusted or to ignore any embedded directives.
- Capability inventory: The skill possesses file-reading capabilities for the whole repository and file-writing capabilities to create the
docs/CRO-AUDIT.mdreport. - Sanitization: No sanitization, escaping, or validation of the content read from the source files is mentioned.
Audit Metadata