apc-new
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill delegates its instructions to a file located at a relative path (
../../.agents/workflows/apc-new.md), which is outside the immediate skill directory. This creates a vulnerability surface where the agent could be manipulated if the content of that external file is compromised. - Ingestion points: The skill loads instructions from the file path
../../.agents/workflows/apc-new.md. - Boundary markers: There are no boundary markers or explicit safety instructions to prevent the agent from executing malicious prompts that might be embedded within the external file.
- Capability inventory: The skill claims to perform 'full workflow orchestration' for product development, implying broad capabilities such as file system access and tool execution.
- Sanitization: No sanitization or integrity verification is performed on the content of the referenced file before the agent follows its instructions.
Audit Metadata