BC extract-youtube-transcript
Extract plain-text transcripts from YouTube videos using a local Python script. Use when the user wants to fetch, extract, or get a transcript from a YouTube video URL, analyze YouTube video content as text, or needs subtitles/captions from a video.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Obfuscation
obf-base64-blobscripts/youtube_cookies.txt:5Long base64-looking blob.youtube.com TRUE / TRUE 1803255432 LOGIN_INFO AFmm…U1X
-
medium Obfuscation
obf-base64-blobscripts/youtube_cookies.txt:15Long base64-looking blob.youtube.com TRUE / TRUE 1806615731 __Se…SID g.a0…P57
-
medium Obfuscation
obf-base64-blobscripts/youtube_cookies.txt:17Long base64-looking blob.youtube.com TRUE / TRUE 1772882709 CONSISTENCY AG2T…wdf
-
low Secrets in code
secret-high-entropy-tokenscripts/youtube_cookies.txt:26High-entropy token-like string (may be an id, hash or a credential).youtube.com TRUE / TRUE 1788434098 __Secure-ROLLOUT_TOKEN CIjR…TAw%3D%3D
Files scanned: 3. 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 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 75Steps. 3 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 486 tokens
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
- +5Description has no quoted example phrases that should trigger the skill
- +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
- +3Description length 249: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (5 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.