CD soul-guardian
Drift detection + baseline integrity guard for agent workspace files with automatic alerting support
Drift detection + baseline integrity guard for agent workspace files with automatic alerting support
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Dangerous commands
cmd-persistencescripts/install_launchd_plist.py:140Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)help="Write plist to this path (default: ~/Library/LaunchAgents/<label>.plist)",
code literal -
medium Dangerous commands
cmd-persistencescripts/install_launchd_plist.py:241Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)sys.stderr.write(f" launchctl bootstrap gui/{uid} {plist_path}\n")code literal -
medium Dangerous commands
cmd-persistencescripts/install_launchd_plist.py:246Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)print("Installed + started (launchctl bootstrap/enable/kickstart).")code literal -
medium Dangerous commands
cmd-persistencescripts/install_launchd_plist.py:249Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)print(f" launchctl bootstrap gui/{uid} {plist_path}")code literal -
medium Exfiltration
intent-browser-credential-storeskill.json:66Accesses a browser credential / cookie store (detector / deny-list definition)"network_egress": "None by default; soul-guardian operates on local files and local state."
detector
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "clawdis"
Process rating: all ten parameters 43/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (soul-guardian) differs from the folder (clawsec-openclaw-soul-guardian)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 85Steps. 23 steps, 1 vague phrases
- 100Execution cost. Instruction body is 1845 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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)
- +3Description length 100: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -34 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.