Caveat verdict
deepsop-genvis
deepsop-genvis-ai
Reads local files AND makes external network calls
AI image and video generation skill using a user-supplied API key to call ai.deepsop.com; purpose is transparent, credentials are user-provided, and no unauthorized actions are present.
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.
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Reads files, encodes data, AND makes external network calls — the obfuscated-exfiltration pattern (data-flow not verified)
LLM02 · ASI03
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Accesses credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Permission integrity
network_out
file_read
credential_access
Findings (6)
Possible hardcoded credential
SKILL.md · code · TOKEN="sk-your_api_key_here
Pipe to python — executes piped content as Python code
README.md · prose · downgraded · | Python
References webhook/callback URL
SKILL.md · code · WEBHOOK_URL
Accesses shell history/config
SKILL.md · prose · downgraded · ~/.zshrc
Python os.environ.get — reads environment variable
scripts/generate_image.py · prose · downgraded · os.environ.get(
Blob URL — may embed executable content
scripts/generate_image.py · prose · downgraded · blob:
Permissions & capabilities
No declared permissions — minimal attack surface.
network_innetwork_outcredential_accessfile_readdata_encoding Thanks — recorded.