apify-generate-output-schema
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to read and analyze untrusted source code to generate schema files. Maliciously crafted comments or strings within the files being analyzed could potentially influence the agent's behavior.
- Ingestion points: The skill reads
actor.json, existing schema files, and source code files (.js, .ts, .py) from the repository. - Boundary markers: There are no explicit instructions to use delimiters or ignore instructions found within the ingested data.
- Capability inventory: The skill identifies data structures and writes multiple JSON files (
dataset_schema.json,output_schema.json,key_value_store_schema.json) and modifiesactor.json. - Sanitization: No sanitization or validation of the ingested code content is performed prior to analysis.
Audit Metadata