Skills
Navigate
skills/agentbay-ai/agentbay-skills/moltbook-hot-posts/Gen Agent Trust Hub

moltbook-hot-posts

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The script scripts/browser-use.py accesses the sensitive file path ~/.config/agentbay/api_key to read and persist the AGENTBAY_API_KEY credential.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a public external source, which may contain instructions intended to manipulate the agent.
  • Ingestion points: Content retrieved from the website moltbook.com as described in SKILL.md examples and executed via the browser agent in scripts/browser-use.py.
  • Boundary markers: None identified in the prompt instructions; there are no delimiters or warnings for the agent to ignore instructions embedded in the retrieved web content.
  • Capability inventory: The skill employs a remote browser agent (agent.browser) capable of executing navigation and data extraction tasks.
  • Sanitization: The script does not implement sanitization or filtering of the content retrieved from the external website before it is returned to the user or processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:37 PM