Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

soul-guardian 👻 · prompt-security | DecimalAI

securityby prompt-security

soul-guardian 👻

prompt-security/soul-guardian

Source prompt-security/clawsec ↗License AGPL-3.0

Drift detection + baseline integrity guard for agent workspace files with automatic alerting support

SkillScore91Maintained

Automatic

Security & AppSec pack

Last verified 8/16/2026

What it changes

Passed 18 of 20 test cases with the skill, and 7 of 20 without it.

Without skill36%

With skill91%

Checks it passed that the model alone missed

The command passes the --actor setup parameter
The response states that actor metadata is best-effort
The response states that changes to memory/*.md files are ignored

and 11 more in the full report

12 fixed8 passed either way2 still failing0 broke

Pass-rate lift: +55 pp
Tokens: +110%
Agent turns: 0%
Response time: -46%

Model gemini-3.6-flashMeasured 8/16/2026v120 of 22 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/prompt-security-soul-guardian/SKILL.md https://app.decimal.ai/s/prompt-security-soul-guardian/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add prompt-security-soul-guardian, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/prompt-security-soul-guardian/ and pins it in .decimal/skills.lock

decimalai skills add prompt-security-soul-guardian

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/prompt-security-soul-guardian/SKILL.md https://app.decimal.ai/s/prompt-security-soul-guardian/SKILL.md

Raw file: /s/prompt-security-soul-guardian/SKILL.md ↗ · machine-readable summary at /s/prompt-security-soul-guardian.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

What is the precise command to install the soul-guardian skill into an OpenClaw agent environment using the Vercel Skills CLI?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies npx skills add prompt-security/clawsec --skill soul-guardian	Missed	Passed

case-05 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md246 lines6 filesincludes scripts

soul-guardian 👻

Protects your agent's core files (SOUL.md, AGENTS.md, etc.) from unauthorized changes with automatic detection, restoration, and user alerting.

Vercel Skills Installation

Install with the Vercel Skills CLI for this harness:

npx skills add prompt-security/clawsec --skill soul-guardian -a openclaw -y

Operational Notes

Required runtime: python3
Optional runtime: openclaw for cron integration, launchctl for macOS scheduling, bash for the demo helper
Side effects: can auto-restore protected files to their approved baseline and writes audit/quarantine state locally
Network behavior: none by default
Trust model: any scheduling is opt-in, but restore mode intentionally overwrites drifted files

Release Artifact Verification

For standalone installs, verify the signed release manifest before trusting SKILL.md, skill.json, or the archive. The skill.json file is the package metadata/SBOM source, and the release pipeline signs checksums.json with the ClawSec release key.

set -euo pipefail

SKILL_NAME="soul-guardian"
VERSION="0.0.9"
REPO="prompt-security/clawsec"
TAG="${SKILL_NAME}-v${VERSION}"
BASE="https://github.com/${REPO}/releases/download/${TAG}"
ZIP_NAME="${SKILL_NAME}-v${VERSION}.zip"
TMP_DIR="$(mktemp -d)"
trap 'rm -rf "$TMP_DIR"' EXIT

RELEASE_PUBKEY_SHA256="711424e4535f84093fefb024cd1ca4ec87439e53907b305b79a631d5befba9c8"

curl -fsSL "$BASE/checksums.json" -o "$TMP_DIR/checksums.json"
curl -fsSL "$BASE/checksums.sig" -o "$TMP_DIR/checksums.sig"

Track record

Benchmark

18 / 20

test cases passed, vs 7 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

prompt-security / clawsec

skills/soul-guardian/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 8/3/2026Version v1Bundled 5 files · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

soul-guardian 👻

Vercel Skills Installation

Operational Notes

Release Artifact Verification

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills