granola-multi-env-setup
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process organizational planning data to automate workspace configuration, which creates a potential surface for malicious instructions to be embedded in that data.
- Ingestion points: User-provided organizational workspace plans and team structures as described in Step 1 of SKILL.md.
- Boundary markers: There are no identified delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The skill is configured with 'Read', 'Write', and 'Edit' tools, allowing it to modify the environment based on the processed planning data.
- Sanitization: The skill lacks explicit validation or sanitization steps for the input data.
- [NO_CODE]: The skill consists entirely of instructional Markdown documentation and YAML configuration, with no executable scripts, source code, or binary files included in the distribution.
Audit Metadata