tracer-wayfinder

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard Git operations (git check-ignore, git add, git checkout) and isolated worktrees to manage local state within the repository. These commands are integral to its functionality as a repository-based planning tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes data from external issue trackers and local files.
  • Ingestion points: Reads from docs/agents/issue-tracker.md, the local .tracer/ state directory, and external issue tracker data.
  • Boundary markers: Uses standard Markdown headers (e.g., ## Question, ## Destination) to delimit data sections, though it lacks explicit instructions to ignore embedded prompts within ticket content.
  • Capability inventory: Possesses capabilities to perform Git operations, write to local configuration files (e.g., .gitignore, .tracer/), and invoke a variety of other agent skills like /tracer-research and /tracer-interview-me.
  • Sanitization: No specific sanitization or filtering logic is defined for the content retrieved from tickets or trackers.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 02:06 PM
Security Audit — agent-trust-hub — tracer-wayfinder