SKILLEMALL.ai

CC video-news-downloader

Automated daily news video downloader with AI subtitle proofreading. Downloads CBS Evening News and BBC News at Ten from YouTube, extracts and proofreads subtitles using DeepSeek, serves videos via HTTP with embedded players. Use when: (1) Setting up automated daily news video downloads, (2) Downloading CBS/BBC news with subtitles, (3) Proofreading subtitle files with AI, (4) Creating local video streaming servers with web players, (5) Managing cron jobs for scheduled video updates.

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 7 files · 2 scripts body ≈ 1 051 tokens Open the sourcegithub.com analyzed 2 d ago

Automated daily news video downloader with AI subtitle proofreading.

As a process C 60/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, progress reporting

GeneratorYouTubeMedia and videotype and topics are labelled automatically from the skill text
JSON
Technical rating
C
68/100
safety, quality, tests
Safety 60%
50
Quality 40%
94
Run on models
none yet
Process rating
C
60/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
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.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 12

  • high Dangerous commands cmd-persistence scripts/setup_cron.sh:22
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v "video_download.py"; echo "$VIDEO_CRON") | crontab -
  • high Dangerous commands cmd-persistence scripts/setup_cron.sh:25
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v "subtitle_proofreader.py"; echo "$PROOFREAD_CRON") | crontab -
Medium and low: 10
  • medium Dangerous commands cmd-persistence scripts/setup_cron.sh:38
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    crontab -l 2>/dev/null | grep -v "video_download.py" | grep -v "subtitle_proofreader.py" | crontab -
    detector
  • low Dangerous commands cmd-cron-mention references/cron-setup.md:22
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention references/cron-setup.md:66
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention references/cron-setup.md:96
    Mentions editing / listing crontab (quoted — discussed, not commanded)
    2. Check syntax: `crontab -l | crontab -`
    quoted
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:22
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v "video_download.py"; echo "$VIDEO_CRON") | crontab -
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:25
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v "subtitle_proofreader.py"; echo "$PROOFREAD_CRON") | crontab -
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:33
    Mentions editing / listing crontab
    crontab -l | grep -E "(video_download|subtitle_proofreader)"
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:38
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -v "video_download.py" | grep -v "subtitle_proofreader.py" | crontab -
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:45
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -E "(video_download|subtitle_proofreader)" || echo "No jobs found"
  • low Dangerous commands cmd-background-process scripts/setup_server.sh:40
    Starts a background / autostarted process
    cd "$dir" && nohup python3 -m http.server $port --bind 0.0.0.0 > /dev/null 2>&1 &

Files scanned: 7. 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 60/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 24 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1051 tokens
  • 100Running it twice. No mutating operations

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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 487: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 24 items
  • +3Output format is stated explicitly
  • +4Has examples (14 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +3All 4 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.