apc-debug

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to load and strictly follow instructions from a relative file path (../../.agents/workflows/apc-debug.md). This behavior creates an ingestion surface where the agent's core logic is retrieved from an external file that is not contained within the skill's own directory.
  • Ingestion points: The agent is instructed to read ../../.agents/workflows/apc-debug.md as its primary source of instructions.
  • Boundary markers: There are no boundary markers or instructions to treat the external content as untrusted; conversely, it is told to follow the content "exactly as written".
  • Capability inventory: Based on the description, the skill involves autonomous debugging, fault isolation, and a "fix loop", which typically requires significant capabilities including file system access and potentially command execution.
  • Sanitization: No sanitization or validation of the external file content is performed by the skill before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 01:17 AM