CF anima
Anima Avatar - Interactive Video Generation Engine. Generates 16:9 videos with dynamic character sprites (Shutiao), synced audio (Fish Audio), and text overlay.
As a process F 47/100 · Will not run — References files that are not bundled: assets/sprites/, assets/backgrounds/, assets/backgrounds/cherry_blossom_bg.png
GeneratorMedia and videoInfrastructuretype and topics are labelled automatically from the skill text
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
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 · 6
✓ No critical or high findings
Medium and low: 6
-
low Exfiltration
exfil-secret-in-urlsrc/batch_generator.js:75Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)const cmd = `curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemi…ent?key=…" -H "Content-Type: application/json" -d @"${payloadPath}"`;placeholder -
low Exfiltration
net-credential-usesrc/batch_generator.js:75Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)const cmd = `curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemi…ent?key=…" -H "Content-Type: application/json" -d @"${payloadPath}"`;known servicequoted -
low Exfiltration
net-credential-usesrc/send_video_pro.js:30Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)const tokenCmd = `curl -s -X POST -H "Content-Type: application/json; charset=utf-8" -d '{"app_id":"${APP_ID}","app_secret":"${APP_SECRET}"}' https://open.feishu.cn/open-apis/auth/v3/tenant_access_tokquoted -
low Exfiltration
net-credential-usesrc/send_video_pro.js:51Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)const uploadVideoCmd = `curl -s -X POST -H "Authorization: Bearer ${token}" -H "Content-Type: multipart/form-data" -F "file_name=anim…mp4" -F "file_type=mp4" -F "duration=${durationMs}" -F "filequoted -
low Exfiltration
net-credential-usesrc/send_video_pro.js:59Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)const uploadImgCmd = `curl -s -X POST -H "Authorization: Bearer ${token}" -H "Content-Type: multipart/form-data" -F "image_type=message" -F "image=@${COVER_PATH}" https://open.feishu.cn/open-apis/im/vquoted -
low Exfiltration
net-credential-usesrc/send_video_pro.js:74Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)const sendCmd = `curl -s -X POST -H "Authorization: Bearer ${token}" -H "Content-Type: application/json; charset=utf-8" -d '{"receive_id": "${TARGET_ID}", "msg_type": "media", "content": "${content}"}quoted
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
name-missingSKILL.md: frontmatter has no `name` - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: assets/sprites/ - warning
missing-refreference to a missing file: assets/backgrounds/ - warning
missing-refreference to a missing file: assets/backgrounds/cherry_blossom_bg.png - warning
missing-refreference to a missing file: assets/sprites/shutiao_base.png
Process rating: all ten parameters 47/100
Will not run. References files that are not bundled: assets/sprites/, assets/backgrounds/, assets/backgrounds/cherry_blossom_bg.png
- 0Tools and files. 4 referenced file(s) missing: assets/sprites/, assets/backgrounds/, assets/backgrounds/cherry_blossom_bg.png
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 100Steps. 71 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2752 tokens
- 100Running it twice. Mutating operations check current state
- 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
- +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 160: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 71 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 30.
External checks
ClawHub: suspicious
Anima is a mostly disclosed avatar-video generator, but it needs Review because user-controlled text, recipient IDs, and paths are placed into shell commands that can execute unintended local commands.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026