SKILLEMALL.ai

BC video2podcast

Convert bookmarked videos from YouTube, X (Twitter), and other sites into a podcast RSS feed hosted on Cloudflare R2. Use when the user says things like "add this to my podcast feed", "add this video to my podcast", "sync my podcast feed", "put this YouTube video in my podcast", or "subscribe to this playlist as a podcast". Manages a persistent episode list and hosts audio files + feed.xml on Cloudflare R2.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Ryan v1.0.2 MIT-0 4 files body ≈ 1 299 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

GeneratorCloudflareYouTubeMedia and videotype and topics are labelled automatically from the skill text
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
72
Quality 40%
92
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 3

  • high Exfiltration intent-browser-credential-store SKILL.md:261
    Accesses a browser credential / cookie store
    yt-dlp --cookies-from-browser chrome "https://x.com/user/status/..."
Medium and low: 2
  • medium Exfiltration intent-browser-credential-store SKILL.md:59
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    "description": "Browser to read cookies from for age-restricted/SABR-protected videos (safari, chrome, firefox, or none). Default: safari. Cookies are read locally and never transmitted.",
    quoted
  • medium Exfiltration intent-browser-credential-store SKILL.md:254
    Accesses a browser credential / cookie store (the skill's own vendor host)
    yt-dlp --cookies-from-browser chrome "https://youtube.com/watch?v=..."
    vendor-host

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 7 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 23 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1299 tokens
  • 100Progress reporting. Reports progress

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 5 example trigger phrases
  • +3Description length 410: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 23 items
  • +4Has examples (13 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

External checks

ClawHub: suspicious
The skill matches its video-to-podcast purpose, but it needs review because it uses browser cookies by default and stores cloud storage credentials in a plaintext local env file.
LLM: suspicious (high) · VirusTotal: · 29 May 2026