outlit
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a 'Fast install' command that downloads a script from the vendor's official website (https://outlit.ai/install.sh) and pipes it directly to bash. While this pattern is often flagged, it is the standard and expected installation method for the vendor's own CLI tool.
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use the
outlitCLI for various tasks, including customer lookups, analytics, and setting up integrations. - [INDIRECT_PROMPT_INJECTION]: The skill has the surface area for indirect prompt injection as it ingests data from external sources such as emails, support tickets, and CRM records.
- Ingestion points: External data enters the agent context through tools like
outlit_list_sources,outlit_search_customer_context, andoutlit_get_timeline(SKILL.md). - Boundary markers: Instructions include rules to cite evidence sources and separate interpretation from evidence, which helps reduce injection risks.
- Capability inventory: The skill interacts with the Outlit API via the
outlitCLI (SKILL.md). - Sanitization: Not explicitly documented in the skill instructions.
Audit Metadata