migrate-app-to-flows
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes source code from the repository (
src/*.ts,src/*.tsx) usinggrepto extract external URLs for themanifest.jsonnetwork permissions. This represents an indirect prompt injection surface where the content of the processed files could potentially influence the agent's behavior during the manifest generation process. - Ingestion points: Processes files in the
src/directory during Step 4 and Step 6. - Boundary markers: None present to distinguish between code and potential embedded instructions.
- Capability inventory: The skill possesses
Edit,Write, andBashcapabilities to modify project files and run audit commands. - Sanitization: The instructions include a mitigation requiring the agent to flag dynamic URLs for manual user verification.
- [COMMAND_EXECUTION]: The skill utilizes
Bashto executegrepfor auditing the codebase and instructs the agent to updatepackage.jsonscripts to use@cognite/cli. These operations are standard for the intended migration task and target vendor-owned infrastructure.
Audit Metadata