flowhunt-skill
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of auditing external communication and task management tools.
- Ingestion points: The skill explicitly directs the agent to scan content from Gmail, Google Calendar, Slack, and task trackers (Jira, Asana, Notion, Linear) to identify patterns.
- Boundary markers: The instructions do not define delimiters or 'ignore embedded instructions' markers when processing data from these external sources in SKILL.md.
- Capability inventory: The skill is designed for agents with access to broad toolsets (claude, codex, gemini, cursor), which may have permissions to read or write data based on the processed inputs.
- Sanitization: There is no evidence of sanitization or validation protocols for external content before it is interpolated into the agent's analysis context.
Audit Metadata