ssot-reconcile
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a TypeScript script using
npx tsxto manage operational state and perform data reconciliation. - [DATA_EXFILTRATION]: The script communicates with
aitable.aiandapi.stripe.com. These are recognized well-known services, and the network activity is consistent with the skill's documented reconciliation logic. - [PROMPT_INJECTION]: Indirect prompt injection surface identified.
- Ingestion points: Data enters the agent context from Postgres database queries, Aitable API responses, and local markdown files processed by
ssot-reconcile.ts. - Boundary markers: Absent. Records and summaries are printed directly to the console and ingested by the agent without delimiters or instructions to ignore embedded commands.
- Capability inventory: The script includes functionality to modify data in Postgres and Aitable (INSERT/UPDATE/DELETE) when executed in
fixmode. - Sanitization: External content is not sanitized or escaped before being presented to the agent.
Audit Metadata