wayfinder

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including issue trackers and project artifacts.
  • Ingestion points: The skill reads project context, ADRs (Architecture Decision Records), and existing planning artifacts from the local file system, and fetches ticket details from Jira or GitHub (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the ingested data.
  • Capability inventory: The skill can write to the local file system (.agents/projects/), create/modify tickets on external platforms (Jira/GitHub), and post comments.
  • Sanitization: There is no evidence of data sanitization or escaping mechanisms for external content before it is processed or stored.
  • [DATA_EXFILTRATION]: The skill interacts with external issue trackers (Jira and GitHub) to publish project maps and tickets.
  • Context: These operations are central to the skill's purpose and target well-known, trusted services. The skill also enforces a rule to never write project artifacts outside the local project directory, mitigating risk to global system files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:37 AM
Security Audit — agent-trust-hub — wayfinder