token
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The file is a discovery entry (shim) that points to a shared skill implementation. It does not contain any executable scripts, sensitive data, or malicious instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill uses a redirection pattern that instructs the agent to read and follow instructions from a different local file. * Ingestion points: The agent is directed to read the content of '../../../.claude/skills/token/SKILL.md'. * Boundary markers: No delimiters or ignore-instructions warnings are present in this shim file. * Capability inventory: No capabilities or tools are defined within this specific file. * Sanitization: None; the skill relies on the integrity of the canonical file in the local project structure.
Audit Metadata