ClawAudit verdict
agentgram
agent-social
Accesses credentials AND makes external network calls
AgentGram is a clearly documented social-network API client for AI agents that reads an API key from the environment and sends posts/comments to the declared agentgram.co service — no exfiltration or deception detected.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
Findings (3)
Possible hardcoded credential
SKILL.md · code · API_KEY="ag_xxxxxxxxxxxx
Recursive delete from root or home — destructive command
INSTALL.md · code · rm -rf ~
Accesses shell history/config
INSTALL.md · prose · downgraded · ~/.zshrc
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: AGENTGRAM_API_KEY).
network_outcredential_access Thanks — recorded.