ClawAudit verdict
tencentcloud-aigc-recog-text
Accesses credentials AND writes files
Tencent Cloud AI-generated text detection service wrapper using user-supplied API credentials; all calls go to the official Tencent Cloud content safety API and the skill is a legitimate text moderation tool.
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 writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Permission integrity
file_read+write
credential_access
package_install
Findings (3)
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
Accesses shell history/config
SKILL.md · code · ~/.zshrc
Python os.getenv — reads environment variable
scripts/main.py · prose · downgraded · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). 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.
credential_accessfile_writepackage_install Thanks — recorded.