philosophy-compliance-workflow

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external codebases, modules, and architectural designs during its review process. This creates a surface where an attacker could embed malicious instructions within comments, string literals, or documentation in the code being analyzed to influence the agent's behavior.
  • Ingestion points: The workflow identifies scope and scans code structures (Step 1 and Step 2 in SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" headers to protect the model from following directions found inside the source files.
  • Capability inventory: The skill is capable of writing artifacts to the local filesystem (~/.amplihack/.claude/runtime/logs/) and invoking the store_discovery tool from the amplihack.memory.discoveries namespace.
  • Sanitization: There is no evidence of sanitization or filtering of the code content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 04:52 PM