account-rotation
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of caller-selected account or profile names to perform high-privilege credential operations.
- Ingestion points: Caller-selected account and profile names used as parameters for rotation tools.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within these strings.
- Capability inventory: The skill employs the rotate_agent_account capability to mutate host and agent credential states through system tools.
- Sanitization: There is no mention of validation, escaping, or filtering of the user-provided account identifiers.
- [COMMAND_EXECUTION]: The skill instructions specify the execution of platform-specific host tools, including claude-acct and caam, to manage and rotate account credentials.
Audit Metadata