kanban-video-orchestrator— agent skill

kanban-video-orchestrator — independently scanned and version-tracked by SaferSkills.

by fengluisobel·Agent Skill·github.com/fengluisobel/ask-dongfeng-hermes

Is kanban-video-orchestrator safe to install?

SaferSkills independently audited kanban-video-orchestrator (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
87/100
●●●●●●●●●
↑ +0 since first scan (87 → 87)Re-scan~30s
Latest scan
ScannedJun 28, 2026 · 30d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings3 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
64
22.4 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 3 flagged

Securityscore 64 · 3 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · optional-skills/creative/kanban-video-orchestrator/SKILL.md
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptoptional-skills/creative/kanban-video-orchestrator/SKILL.md· markdown
60 
61From the answer, classify the style category. The style determines which
62follow-up questions to ask. **Do not ask all questions at once.** Ask 2-4 at a
63time, listen, then proceed. Make reasonable assumptions whenever the user
64implies an answer.
Occurrences
1 occurrence · at L62
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25668b030f55bcd484arubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · optional-skills/creative/kanban-video-orchestrator/references/intake.md
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptoptional-skills/creative/kanban-video-orchestrator/references/intake.md· markdown
162 
163- **Asking 10 questions at once.** Maximum 4 per turn.
164- **Asking for things the brief already implies.** If the user said "music video for my trac
… (34 chars elided on L164)
165- **Failing to classify before drilling in.** Tier-1 questions depend on classification; mix
… (25 chars elided on L165)
166- **Treating "make a video" as enough to proceed.** Always confirm the three baseline questi
… (4 chars elided on L166)
Occurrences
1 occurrence · at L164
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25612211d7a427c799arubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · optional-skills/creative/kanban-video-orchestrator/references/kanban-setup.md
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptoptional-skills/creative/kanban-video-orchestrator/references/kanban-setup.md· markdown
270 
2716. **The `audio/` and `taste/` dirs are populated BEFORE firing the kanban.**
272Don't ask the director's pipeline to source these — copy at setup time.
273 
2747. **`brief.md` is read-only after setup.** If the brief changes during
Occurrences
1 occurrence · at L272
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25615dae9807bd892c6rubric 365aacaView on GitHub
Supply chainscore 100 · 0 findings
All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.