scanner-bridge
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources (GitHub issue titles and bodies), creating a potential attack surface.
- Ingestion points:
SKILL.mddefines capabilities to fetch issue titles and body content via the GitHub REST API. - Boundary markers: The instructions do not define boundary markers or explicit "ignore embedded instructions" directives for the data retrieved from issues.
- Capability inventory: The skill maintains read-only access to repository workflow files and the GitHub REST API for issues and pull requests.
- Sanitization: There is no mention of sanitization, escaping, or validation of the fetched issue content before it is normalized into the structured JSON output.
- [EXTERNAL_DOWNLOADS]: The skill references and fetches rules and documentation from well-known and official sources, including GitHub and the axe-core ruleset by Deque Systems.
Audit Metadata