stream-feeds-migration
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves fetching and analyzing up to 100 raw activities and reaction data from the Stream API, which are stored in
v3sync-sample.json. This data consists of untrusted user-generated content that could potentially contain malicious instructions designed to manipulate the agent's behavior during the analysis phase.\n - Ingestion points: The analysis phase reads the contents of
v3sync-sample.json, which contains unflattened and unmodified payloads from the Stream v2 API.\n - Boundary markers: The instructions do not define boundary markers or 'ignore' instructions for the agent to follow when processing the sampled JSON data.\n
- Capability inventory: The agent has access to
Bash(configured to runpython3,ls, andgetstream),Read,Glob, andGreptools.\n - Sanitization: The
fetch_sample.pyscript retrieves raw data without sanitization, and the agent is instructed to look for 'real field names and nesting' within these raw payloads.
Audit Metadata