apc-impl

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to load and follow instructions from a local file path (../../.agents/workflows/apc-impl.md).
  • Ingestion points: The agent is directed to read and execute logic from a file located at ../../.agents/workflows/apc-impl.md.
  • Boundary markers: No boundary markers or instructions to ignore potential commands within the loaded file are present.
  • Capability inventory: The skill's stated purpose is to "Build the plugin's DSP and UI code," implying capabilities for code generation and file system access.
  • Sanitization: There is no evidence of sanitization or content validation for the loaded file.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 07:44 PM