AD aegis-audit
Deep behavioral security audit for AI agent skills and MCP tools. Performs deterministic static analysis (AST + Semgrep + 15 specialized scanners), cryptographic lockfile generation, and optional LLM-powered intent analysis. Use when installing, reviewing, or approving any skill, tool, plugin, or MCP server — especially before first use. Replaces basic safety summaries with full CWE-mapped, OWASP-tagged, line-referenced security reports.
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitySKILL.md:168Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Dockerfile Analyzer | Privilege escalation, secrets in ENV/ARG, unpinned images |
-
low Risky intent
intent-offensive-securitySKILL.md:173Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Combo Analyzer | Multi-capability attack chains (exfiltration, C2, ransomware) |
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "url"
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2358 tokens
- low 14 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 441: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.