Skills/ClawHub/media-audio-edition

media-audio-edition@5.0.0

VERIFIED· install only

Publisher claims: "Turn a blog post or newsletter into a podcast episode people can follow by ear. Two AI hosts talk the post through, with a hook, a roadmap, the post's main points with an example each and a recap, in voices the user picks, plus 5-second intro and outro music, a transcript, show notes, a LinkedIn post and an optional 45-second captioned clip. One host, a 2-minute brief or a straight reading are options. Use when someone wants a podcast or audio version of a post or newsletter. Nothing is spent until they approve the outline, script, voices and maximum cost in one message." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher scrollport · publishing for 5 daysInstalls 37Last detonated 5d ago
$clawhub install media-audio-edition
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

CRITICAL
Fake instruction boundary tagSKILL.md:342 · Fake instruction boundary tag- music: `{"prompt": "<prompt>", "music_length_ms": 7000, "force_instrumental": true}`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
False input termination markerSKILL.md:313 · False input termination marker — attempts to end user input section--- end of script ---Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈7,810 tok
1 file · 8 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.