escalation-flagger
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill relies on external configuration files (CLAUDE.md and matter.md) to define its escalation logic and context. If these files were to contain malicious instructions, they could potentially influence how the agent characterizes issues or names approvers. * Ingestion points: The skill reads data from
/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md and matter-specific matter.md files. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when reading these files. * Capability inventory: The skill has the ability to read and write files within the plugin directory structure (/.claude/plugins/config/claude-for-legal/commercial-legal/). * Sanitization: There is no evidence of sanitization or validation of the content read from the configuration files before it is processed by the agent.
Audit Metadata