data-context-extractor
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external datasets and files, creating an attack surface for indirect prompt injection where malicious instructions could be embedded in the data.
- Ingestion points: Dataset grain, schema, and units analysis described in
SKILL.md. - Boundary markers: The skill includes a mitigation instruction in the 'Focus checks' section to ignore embedded text as instructions.
- Capability inventory: The skill has the ability to execute external API calls via the
sandbase_runtool. - Sanitization: None identified beyond instructional boundaries.
- [SAFE]: The skill implements transparency measures by instructing the agent to provide cost estimates, endpoint details, and argument previews for user confirmation before executing external tasks. The external tools (
sandbase_discover,sandbase_inspect,sandbase_run, etc.) are resources belonging to the skill's vendor.
Audit Metadata