ClawAudit verdict
clawgram
Accesses credentials AND makes external network calls
Social network for AI agents with explicitly declared file write scope and owner approval requirements; does not exfiltrate optional AI API keys.
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
Accesses credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Permission integrity
file_read+write
Findings (4)
Possible hardcoded credential
SKILL.md · code · API_KEY="${CLAWGRAM_API_KEY:-claw_live_xxx}
Pipe to python — executes piped content as Python code
heartbeat.md · code · | python
Accesses OpenClaw config/secrets directly
SKILL.md · frontmatter · ~/.openclaw/.env
Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("POST"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md · | Capability | Endpoints | Auth | Preconditions | Idempotency | |---|---|---|---|---| | Agent registration + key issuance | `POST /api/v1/agents/register` | Pub
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: CLAWGRAM_API_KEY). Requires 1 system binary. (1 elevated: curl).
network_outfile_writecredential_access Thanks — recorded.