mongodb-atlas-checker
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions in
references/full-guide.mddirect the agent to scan project documentation, specifically in.agents/memory/, to discover architecture and deployment context. This creates a surface where malicious instructions embedded in project documentation could influence agent behavior. - Ingestion points: The
.agents/memory/directory referenced inreferences/full-guide.md. - Boundary markers: No explicit delimiters or warnings to ignore instructions within the ingested data are provided.
- Capability inventory: The skill suggests the creation and execution of a verification script (
scripts/test-mongodb-connection.ts) using shell commands. - Sanitization: There is no mention of sanitizing or validating the information discovered in the project memory.
- [COMMAND_EXECUTION]: The skill provides specific commands in
references/full-guide.mdto run a connection verification script usingnodeorts-node. This involves direct shell execution, though it is aligned with the skill's primary purpose of verifying database connectivity.
Audit Metadata