The Agent Skills Directory

[DATA_EXFILTRATION]: Accesses local credential stores (~/.config/moltbook/credentials.json and ~/.openclaw/auth-profiles.json) to retrieve API keys. While accessing platform-specific auth files is common for integrations, these files contain sensitive information.\n- [DATA_EXFILTRATION]: Performs network operations using curl to https://www.moltbook.com. This domain is external and not included in the default whitelist.\n- [PROMPT_INJECTION]: The skill processes untrusted data from an external social network, which could contain malicious instructions for the agent.\n
Ingestion points: Data is fetched from the Moltbook API in scripts/moltbook.sh via the hot, new, and post commands.\n
Boundary markers: No markers are used to separate fetched content from the agent's instructions.\n
Capability inventory: The skill allows creating posts and replies via curl in scripts/moltbook.sh.\n
Sanitization: No sanitization or validation of the fetched data is performed.\n- [COMMAND_EXECUTION]: The script scripts/moltbook.sh executes curl and other CLI tools, interpolating variables into arguments and JSON payloads.\n- [EXTERNAL_DOWNLOADS]: Installation instructions refer to an external GitHub repository (github.com/LunarCmd/moltbook-skill) from an unverified author.

moltbook