apify-common-errors
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data from Actor logs and run metadata, which presents a surface for indirect prompt injection.\n
- Ingestion points: Retrieves Actor run logs and status messages using
client.run().log().get()andclient.run().get()as shown inSKILL.md.\n - Boundary markers: The skill content does not define specific delimiters or instructions to the agent to disregard potential commands embedded within the logs.\n
- Capability inventory: The skill's environment includes
Bash(curl),Bash(apify), andBash(npm)capabilities.\n - Sanitization: There is no evidence of sanitization or filtering applied to the log data before it is processed by the agent.\n- [COMMAND_EXECUTION]: Provides standard shell commands using
curl,apify, andnpmfor platform health checks, authentication verification, and local build testing.\n- [DATA_EXFILTRATION]: Utilizes the$APIFY_TOKENenvironment variable to authenticate requests to official Apify API endpoints (api.apify.com) for diagnostic purposes.
Audit Metadata