Caveat verdict
suhe-selfie
suhe
Executes processes AND makes external network calls
Image editing and messaging skill that uses Alibaba DashScope API to edit a reference image and sends results via OpenClaw messaging; all operations are transparent, user-triggered creative tasks with no suspicious data collection.
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.
Executes processes AND makes external network calls — may exfiltrate command output
LLM02 · LLM06 · ASI03
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Installs packages AND executes processes — opaque dependency chain with execution
LLM03 · ASI04
Permission integrity
network_out
credential_access
package_install
Findings (6)
References child_process — can spawn system processes
SKILL.md · code · child_process
Possible hardcoded credential
scripts/suhe-selfie.sh · prose · downgraded · API_KEY='your_api_key_here
Accesses sensitive environment variables
SKILL.md · code · process.env.FAL_KEY
References agent memory files
README.md · code · MEMORY.md
Popular HTTP library — network access
scripts/suhe-selfie.ts · prose · downgraded · axios
POSTs data to external URL
scripts/suhe-selfie.ts · prose · downgraded · .post(
'http://
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_accessprocess_execpackage_install Thanks — recorded.