Skills/ClawHub/sillytavern-cards-skill

sillytavern-cards-skill@0.1.0

VERIFIED· install only

Publisher claims: "Import and roleplay with SillyTavern-compatible character cards (TavernAI V2/V3 PNG format)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher pearyj · publishing for 245 daysInstalls 1,318Last detonated 14 min ago
$clawhub install sillytavern-cards-skill
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-16 and scored it 80/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:220 · Instructs the agent to modify its persistent memory or instruction filesIf the card has `character_book` entries, append them to `~/.openclaw/MEMORY.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentSKILL.md:235 · HTML comment carrying imperative instructions to the agentALWAYS ACTIVEFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:326 · Instructs the agent to modify its persistent memory or instruction filesA lightweight mode for trying out a character or having a casual conversation. **Does not modify SOUL.md or MEMORY.md.** The character exists only in the current conversation context.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:331 · Instructs the agent to modify its persistent memory or instruction files2. Do NOT modify SOUL.md. Do NOT modify MEMORY.md.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentSKILL.md:225 · HTML comment carrying imperative instructions to the agentALWAYS ACTIVE entries are always includedFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:218 · Instructs the agent to modify its persistent memory or instruction files### Step 2: Write lorebook to MEMORY.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:301 · Instructs the agent to modify its persistent memory or instruction files### Step 2: Write lorebook to MEMORY.md (same as Play mode)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Pipe-to-shell patterncn/SKILL.md:137 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -s "https://charavault.net/api/cards?q=<搜索词>&limit=10&sort=most_downloaded&nsfw=false" | node -e "Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Fake system instruction headerSKILL.md:212 · Fake system instruction header — mimics internal system structure## System InstructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Pipe-to-shell patternSKILL.md:122 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -s -H "User-Agent: SillyTavern" "https://api.chub.ai/search?search=<query>&first=10&page=1&sort=last_activity_at&nsfw=false" | node -e "Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Pipe-to-shell patternSKILL.md:137 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -s "https://charavault.net/api/cards?q=<query>&limit=10&sort=most_downloaded&nsfw=false" | node -e "Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Pipe-to-shell patterncn/SKILL.md:122 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -s -H "User-Agent: SillyTavern" "https://api.chub.ai/search?search=<搜索词>&first=10&page=1&sort=last_activity_at&nsfw=false" | node -e "Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06

Cost to the agent

Instructions loaded
≈6,444 tok
2 files · 8 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.