AF sentryskills
SentrySkills - Automatic security guard that runs on EVERY task. Protects against prompt injection, data leaks, unsafe commands, and code vulnerabilities with zero external dependencies.
As a process F 46/100 · Will not run — References files that are not bundled: install/first_time_setup.md
IntegrationSoftware developmentAI and agentsSecuritytype and topics are labelled automatically from the skill text
How to improve
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securityREADME.md:61Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)**Predictive**: Resource exhaustion, scope creep, privilege escalation, data exfiltration
detector -
low Dangerous commands
cmd-privilegeshared/scripts/predictive_analysis.py:178Privilege escalation / world-writable permissions (string literal in code, not executed)(r"\bsetuid\b|\bsetgid\b", 0.45, "setuid/setgid manipulation"),
code literal -
low Risky intent
intent-offensive-securitySKILL.md:164Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Privilege escalation warning
Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: install/first_time_setup.md
Process rating: all ten parameters 46/100
Will not run. References files that are not bundled: install/first_time_setup.md
- 0Tools and files. 1 referenced file(s) missing: install/first_time_setup.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 72 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1592 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 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)
- +2Single-language instructions
- +3Description length 186: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 72 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.
External checks
ClawHub: suspicious
This looks like a local security guard rather than malware, but it persistently changes agent behavior and can store raw prompts and responses, so it needs review before installation.
LLM: suspicious (high) · VirusTotal: · 29 May 2026