Caveat verdict
social-media-analysis
Accesses credentials AND makes external network calls
Reads social media URLs from Feishu (Lark) tables, downloads media, and generates summaries back into the same table — network access matches stated social media analytics workflow.
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 (8)
Possible hardcoded credential
SKILL.md · code · SECRET="<your_secret>
<script> tag in markdown — potential code injection
scripts/backfill-content-analysis-by-source.js · prose · downgraded · <script
Uses exec() — may execute shell commands
scripts/backfill-content-analysis-by-source.js · prose · downgraded · exec(
References child_process — can spawn system processes
scripts/parse-bilibili.js · prose · downgraded · child_process
Uses spawn() — can execute external programs
scripts/run_backfill.js · prose · downgraded · spawn(
Python os.getenv — reads environment variable
scripts/backfill-content-analysis-by-source.py · prose · downgraded · os.getenv(
Uses XMLHttpRequest — network access
scripts/backfill-content-analysis-by-source.py · prose · downgraded · XMLHttpRequest
Node http/https module — low-level network access
scripts/download-xiaohongshu-album.js · prose · downgraded · require('https')
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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.