glean-core-workflow-a
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from enterprise data sources via the Glean API, which may contain instructions targeting the agent.
- Ingestion points: Data enters the agent's context through search result snippets and AI chat responses defined in
SKILL.md(Step 1 and Step 2). - Boundary markers: Absent. The skill does not use delimiters or provide instructions to the agent to treat the fetched content as untrusted data.
- Capability inventory: The skill allows access to
Read,Write,Edit,Grep, andBash(supporting npm and curl), providing a significant surface for exploitation if malicious instructions are followed. - Sanitization: The skill prints API responses directly to the console without filtering or validation.
- [EXTERNAL_DOWNLOADS]: The skill communicates with Glean's official API endpoints to perform search and chat operations.
- Details: Instructions show network requests to
${GLEAN}/client/v1/search,/chat, and/autocompleteusing thefetchAPI.
Audit Metadata