context-discovery

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown-based instructions and logic templates for the AI agent to follow. It does not contain scripts, binaries, or command-line execution patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from user inputs and external references (such as GitHub URLs or slide materials) to populate its '8 context elements'.
  • Ingestion points: User input text and MATERIALS field in Step 3 of SKILL.md.
  • Boundary markers: Absent; the instructions do not explicitly tell the agent to treat input as data only or use specific delimiters.
  • Capability inventory: None; the skill does not define any tools, file-system access, or network capabilities.
  • Sanitization: Absent; there is no logic to filter or escape the content of the user's input.
  • Risk assessment: Although a surface for indirect prompt injection exists, the lack of any actionable capabilities (like shell execution or data exfiltration) within this skill makes the actual risk negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:39 PM
Security Audit — agent-trust-hub — context-discovery