effect-streams-pipelines
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill directs the agent to analyze local source files within the
docs/effect-source/directory to understand library implementations. This constitutes a surface where the agent could ingest and act upon instructions hidden within that codebase. - Ingestion points: Files in
docs/effect-source/accessed viaRead,Grep, andGlobtools. - Boundary markers: Absent. The skill does not provide instructions to the agent to treat content in these files as untrusted or to ignore embedded instructions.
- Capability inventory: The agent has
WriteandEditcapabilities, which could be used to perform unauthorized changes if the agent is influenced by poisoned source data. - Sanitization: Absent. There is no mention of filtering or validating the content of the files before the agent processes them.
Audit Metadata