Caveat verdict
finance-report-analyzer
Accesses credentials AND makes external network calls
Analyzes uploaded financial data files and generates reports using local Python scripts; reads Feishu credentials from user-controlled config for optional file delivery, with no unauthorized data exfiltration.
Automated static analysis — not a human review. Caveat 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 Caveat 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
credential_access
Findings (4)
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
Instruction-prose smuggling shape detected: collects a sensitive target ("credentials") 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 · 1. **Feishu chat file attachment** — Download via API: ```bash # Get token TOKEN=$(curl -s -X POST 'https://open.feishu.cn/open-apis/auth/v3/tenant_access_token
os.system/popen — direct OS command execution
scripts/generate_report.py · prose · downgraded · os.system(
subprocess execution — runs system commands from Python
scripts/generate_report.py · prose · downgraded · subprocess.run(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_access Thanks — recorded.