remember
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and displays content from a remote NocoDB database, which serves as an untrusted data source that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data is retrieved from the NocoDB API in
scripts/manage_items.pyvia thefind_itemandlist_itemsfunctions, specifically the 'Name', 'Content', 'Location', 'Type', and 'Note' fields. - Boundary markers: There are no boundary markers or instructions to the agent to treat the retrieved database content as untrusted or to ignore any embedded commands within the text.
- Capability inventory: The skill possesses network capabilities (HTTP GET/POST/PATCH/DELETE) to interact with the database and file system capabilities to write downloaded images to the
tmp/directory. - Sanitization: The script performs no sanitization or escaping of the text returned from the database before printing it to the console for the agent to read.
Audit Metadata