apify-hello-world
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data scraped from external websites via Apify Actors. This data enters the agent's context and could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Scraped data is retrieved from Apify datasets via the
apify-clientlibrary inSKILL.mdandreferences/examples.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes the retrieved text.
- Capability inventory: The skill is configured to allow file system writes and command execution (npm, npx, node).
- Sanitization: Example code provides basic text truncation but no formal sanitization against prompt injection patterns.
- [DYNAMIC_EXECUTION]: The skill guides the agent to create and run local scripts to interact with the Apify platform.
- Evidence:
SKILL.mdprovides instructions for writing a script (hello-apify.ts) and executing it usingnpx tsxornode. This represents standard script generation from provided templates for developer tooling.
Audit Metadata