wayfinder-vault-tracker
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read, claim, and resolve tickets and research notes stored within a vault system. This ingestion of untrusted or external data serves as an attack surface for indirect prompt injection. 1. Ingestion points: Vault files located in wayfinder/{effort}/issues/ and wayfinder/{effort}/research/. 2. Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the notes it processes. 3. Capability inventory: The skill utilizes the hatchdoor MCP tools to perform file system operations including listing, reading, and writing to the vault. 4. Sanitization: There is no evidence of content sanitization or validation to prevent the agent from executing instructions found within the vault notes.
Audit Metadata