escalation-flagger
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill's instructions or workflow.
- [DATA_EXFILTRATION]: The skill interacts with local files such as
~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.mdto retrieve escalation logic and matter context. These operations are confined to the local filesystem within designated plugin directories and do not involve unauthorized network communication or access to sensitive system credentials. - [PROMPT_INJECTION]: The instructions do not contain attempts to override agent safety guidelines or bypass behavioral constraints. The skill acts as a structured drafting tool and does not ingest untrusted external data that could lead to indirect injection.
- [COMMAND_EXECUTION]: The skill does not perform any shell command execution or privilege escalation. It only drafts content for the user to review and manually send.
Audit Metadata