w-wayfinder

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project 'maps' from the local file system, which creates a surface for indirect prompt injection if these files contain malicious instructions meant to influence the agent.
  • Ingestion points: Map files are loaded during the 'Work through' mode as described in SKILL.md.
  • Boundary markers: The instructions do not provide explicit delimiters or warnings to ignore instructions found within the data files.
  • Capability inventory: The skill is limited to reading and writing Markdown files. It does not have access to shell execution, network exfiltration tools, or dynamic evaluation capabilities.
  • Sanitization: There is no logic for sanitizing or filtering input from the map files.
  • [NO_CODE]: The skill consists solely of instructional Markdown and does not include any scripts, binaries, or configuration files that trigger executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 06:21 PM
Security Audit — agent-trust-hub — w-wayfinder