The Agent Skills Directory

[DATA_EXFILTRATION]: The skill reads API credentials from ~/.config/moltbook/credentials.json and ~/.openclaw/auth-profiles.json. This is the intended behavior for authenticating with the Moltbook API. The extracted API_KEY is only transmitted to the official service domain https://www.moltbook.com/api/v1 via Bearer authentication.
[COMMAND_EXECUTION]: The bash script scripts/moltbook.sh uses standard system utilities including curl, jq, grep, and sed to perform API operations and parse responses. These operations are restricted to the primary purpose of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection as it retrieves untrusted user-generated content (posts and comments) from Moltbook.
Ingestion points: Content is ingested through GET requests in scripts/moltbook.sh (commands hot, new, and post).
Boundary markers: The skill does not provide explicit delimiters or instructions to the agent to ignore embedded commands in the fetched data.
Capability inventory: The skill has network access (curl) and local file read/write capabilities (credentials and reply logs).
Sanitization: There is no evidence of sanitization or filtering of the external content before it is passed to the agent context.

moltbook