role-browser
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is required to read local configuration files which could influence agent behavior if those files are modified by an attacker.
- Ingestion points: The skill MUST read
.agent-team/rules/index.mdbefore proceeding. - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the ingested file content.
- Capability inventory: The skill executes the
agent-team role listCLI command. - Sanitization: There is no evidence of sanitization or schema validation for the data read from the local file system.
Audit Metadata