ae-team
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill incorporates security best practices by instructing the agent to discover real resource identifiers before execution and requiring explicit user confirmation for high-risk delete operations.
- [INDIRECT_PROMPT_INJECTION]: The skill documents an interactive surface where the agent processes external data and executes commands based on user interaction. 1. Ingestion points: Data enters the agent context from the stdout of 'ae-cli' (e.g., 'pendingQuestion' and 'output' fields) as described in 'SKILL.md' and 'references/run-result.md'. 2. Boundary markers: Absent. 3. Capability inventory: Management of platform resources (teams, runs, artifacts) via 'ae-cli' commands as documented across the 'references/' directory. 4. Sanitization: Absent; the agent is instructed to pass user input and tool output verbatim.
Audit Metadata