Caveat verdict
openclaw-podcast
Reads workspace memory files and sends their content to the declared Superlore.ai API to generate audio briefings; the network destination and data flow are explicitly disclosed.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
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.
Findings (9)
Accesses shell history/config
SKILL.md · frontmatter · ~/.zshrc
Possible hardcoded credential
scripts/setup-crons.js · prose · downgraded · API_KEY="${apiKey}
References agent memory files
SKILL.md · frontmatter · MEMORY.md
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · quietly
Popular HTTP library — network access
references/styles.md · code · got
References child_process — can spawn system processes
scripts/setup-crons.js · prose · downgraded · child_process
Node http/https module — low-level network access
scripts/generate-episode.js · prose · downgraded · require('https')
Accesses sensitive environment variables
scripts/generate-episode.js · prose · downgraded · process.env.SUPERLORE_API_KEY
Base64 encoding/decoding
scripts/generate-episode.js · prose · downgraded · Base64-encode
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
Requires 1 environment variable. (1 sensitive: name: SUPERLORE_API_KEY).
credential_access Is this flag fair?
Thanks — recorded.