storage
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface detected via the storage retrieval mechanism.
- Ingestion points: Data retrieved from the
netnode_kvtable via SQL queries (e.g.,SELECT value FROM netnode_kv) inSKILL.mdenters the agent's context. - Boundary markers: The skill does not provide delimiters or specific instructions for the agent to treat retrieved storage values as untrusted external data.
- Capability inventory: The skill grants access to the
Bashtool as defined in the YAML frontmatter, providing an execution path if the agent obeys instructions injected into the storage. - Sanitization: There is no documented validation or sanitization of the retrieved
valuestrings before they are processed by the agent.
Audit Metadata