Caveat verdict

ai-podcast

delonix-ai-podcast

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

PDF/text to podcast conversion using MagicPodcast API with the user's own MAGICPODCAST_API_KEY; credential_access reads the user's key and network_out goes to the documented magicpodcast.app endpoint for the stated content generation purpose.

⚠ 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.

65
security
70
transparency
70
maintenance

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="<your_api_key>

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("paste"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · 1. Ask one question at a time, then wait for the user's reply before asking the next. 2. If API key is missing or invalid, stop and say: `It's free to get start

Permissions & capabilities

Requires 2 environment variables. (1 sensitive: MAGICPODCAST_API_KEY). Requires 2 system binaries. (1 elevated: curl).

network_outcredential_access

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API