workflow-feature-flag
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data from Sentry issues and Supabase logs to monitor rollout health and perform root-cause analysis. This creates a surface for indirect prompt injection where malicious content embedded in logs or error messages could influence the agent's analysis or decision-making.
- Ingestion points: Fetches runtime data from
SKILL.mdusingplugin-sentry-sentry:search_issuesandplugin-supabase-supabase:get_logs. - Boundary markers: No explicit delimiters or instructions to the agent to ignore embedded commands within the processed data are provided.
- Capability inventory: The agent uses
plugin-sentry-sentry:analyze_issue_with_seerto process the ingested data, which could lead to automated decisions based on untrusted input. - Sanitization: No validation or sanitization of log/error content is performed before it is analyzed by the agent.
Audit Metadata