context-discovery

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation guide for using productivity-focused MCP tools. It does not contain executable code, installation scripts, or instructions that would compromise the agent's safety guidelines.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by design, including codebase files, git history, and external documentation lookup via context7. While this introduces an attack surface for indirect prompt injection, it is the primary purpose of the skill and falls within normal operational parameters.
  • Ingestion points: Local source code (via fff, sem), session history (ctx), and external documentation (context7).
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: File reading, history retrieval, and documentation querying.
  • Sanitization: Relies on the underlying agent platform's internal guardrails for processing ingested text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 04:22 AM
Security Audit — agent-trust-hub — context-discovery