gsp-brand-audit
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute directory creation commands (
mkdir -p) to set up the audit output structure. - [EXTERNAL_DOWNLOADS]: The skill utilizes the
WebFetchtool to retrieve content from brand-related URLs provided by the user or defined in project briefs. - [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface through the ingestion of external data. \n
- Ingestion points: External content retrieved via
WebFetchand user-provided brand descriptions in theBRIEF.mdfile. \n - Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions to isolate ingested data from the agent's core instructions. \n
- Capability inventory: The agent has access to file-writing, limited shell command execution, and sub-agent spawning capabilities. \n
- Sanitization: No explicit sanitization or validation of external web content is performed before it is analyzed by the auditor agent.
Audit Metadata