bluesky-cascade-fetch

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a legitimate data utility for the Bluesky social platform. Analysis of the scripts and instructions confirms they are focused solely on data retrieval and processing.
  • [CREDENTIALS_UNSAFE]: The skill avoids hardcoded secrets. It correctly utilizes environment variables for authentication and includes a mask_secret utility to prevent accidental exposure of credentials in logs or configuration summaries.
  • [COMMAND_EXECUTION]: The Python script does not utilize any functions capable of shell command execution (such as os.system or subprocess.run). All operations are performed using standard library functions for HTTP and file I/O.
  • [EXTERNAL_DOWNLOADS]: Network operations are limited to fetching structured JSON data from official Bluesky API hosts (public.api.bsky.app and bsky.social). No executable code or scripts are downloaded from the internet.
  • [PROMPT_INJECTION]: The skill's metadata and instructional content do not contain patterns intended to bypass AI safety guardrails or override system instructions.
  • [DATA_EXFILTRATION]: There is no evidence of unauthorized data transfer. The skill only communicates with the designated service provider to retrieve public social media content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:19 PM