tigris-objects

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides documentation and examples for using the tigris CLI tool to manage storage objects. All operations described (listing, copying, moving, deleting) are standard administrative tasks for a storage service.
  • [SAFE]: The presign command allows for temporary URL generation, which is a documented feature of the Tigris service for sharing access without providing long-term credentials. The example provided uses a placeholder access key (tid_AaBb) and does not expose actual secrets.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection through the processing of untrusted data from external storage. (1) Ingestion points: Data enters the context via tigris ls, tigris stat, and tigris objects get as described in SKILL.md. (2) Boundary markers: None present in the instructions. (3) Capability inventory: The skill facilitates network operations (CLI interaction with Tigris API) and file system writes (tigris cp, tigris objects get --output). (4) Sanitization: None present for the content of retrieved objects.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:12 AM