charted-red
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external files to guide code generation, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill reads contents from
${designDocPath}and${testFilePath}to provide context for the implementation task. - Boundary markers: There are no explicit delimiters or safety instructions (e.g., "ignore embedded instructions") defining the boundaries between the agent's instructions and the untrusted file content.
- Capability inventory: The skill is capable of generating code and writing it to the local file system via the
${testFilePath}. - Sanitization: The skill lacks validation or sanitization mechanisms to filter malicious instructions or code snippets that might be present in the design documentation.
Audit Metadata