github
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external content from GitHub (issues, comments, repository metadata), creating an attack surface for indirect prompt injection.\n
- Ingestion points: Data retrieved via Apideck unified API methods like
tickets.listandcomments.listas described inSKILL.md.\n - Boundary markers: Absent in the provided instruction templates.\n
- Capability inventory: The skill enables read/write access to GitHub via Apideck SDK and Proxy API, as demonstrated in
SKILL.md.\n - Sanitization: Absent; no explicit sanitization or filtering of remote content is mentioned.\n- [EXTERNAL_DOWNLOADS]: The skill references and downloads configuration and documentation from trusted sources including Apideck's official developer portal and GitHub's official documentation.\n
- Fetches OpenAPI specifications from
specs.apideck.com.\n - References official SDKs and documentation from
developers.apideck.comanddocs.github.com.
Audit Metadata