Skill Compiler

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 8:43 AM UTC
• Version: 0.2.0

Overview

This skill is a local skill-artifact compiler with no bundled executable code, network use, or secret handling, though users should be aware it can read skill files under a chosen skills directory when run.

Install only if you want a local compiler for skill files. Review or supply the referenced scripts before relying on it, and avoid enabling the generic execute trigger unless your runtime restricts it to explicit skill invocations.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (11)

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

md

For each input `SKILL.md`, compiler generates sibling artifacts:

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

md

For each input `SKILL.md`, compiler generates sibling artifacts:

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md

For each input `SKILL.md`, compiler generates sibling artifacts:

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md

- `SKILL.struct.json` (canonical runtime structure)

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md

- `SKILL.struct.json` (canonical runtime structure)

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

Using the generic trigger word "execute" creates a realistic risk of accidental skill invocation because it overlaps with normal user phrasing. In an agent ecosystem, unintended activation can cause commands or follow-on actions to run in contexts where the user did not explicitly mean to invoke this skill.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 80% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 5)May include surrounding context.

md

"headings": [
    {
      "level": 2,
      "name": "name: skill-compiler\ndescription: Compile SKILL.md files into runtime artifacts (SKILL.struct.json and SKILL.toon), verify freshness/health, and prepare portable publish-ready skill folders for ClawHub-style registries.\ncontract_version: v0\nquick_cmd: skills/public/skill-compiler/scripts/compile-skill --skill skills/todoist/SKILL.md\nrisk_level: safe\ncapabilities:\nbins: [bash, mdquery, jq, toon]\nnetwork: false\nsecrets: []\ndry_run_cmd: skills/public/skill-compiler/scripts/check-env\ncompat:\nos: [linux, macos]\narch: [x64, arm64]\nshell: [bash]\nowner: matt\nlast_tested: 2026-03-08\nrollback: remove skills/public/skill-compiler and revert commit\ncategory: ops\ninputs_min: []\ncost_hint: low",
      "text": ""
    },
    {

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 80% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 35)May include surrounding context.

md

"headings": [
    {
      "level": 2,
      "name": "name: skill-compiler\ndescription: Compile SKILL.md files into runtime artifacts (SKILL.struct.json and SKILL.toon), verify freshness/health, and prepare portable publish-ready skill folders for ClawHub-style registries.\ncontract_version: v0\nquick_cmd: skills/public/skill-compiler/scripts/compile-skill --skill skills/todoist/SKILL.md\nrisk_level: safe\ncapabilities:\nbins: [bash, mdquery, jq, toon]\nnetwork: false\nsecrets: []\ndry_run_cmd: skills/public/skill-compiler/scripts/check-env\ncompat:\nos: [linux, macos]\narch: [x64, arm64]\nshell: [bash]\nowner: matt\nlast_tested: 2026-03-08\nrollback: remove skills/public/skill-compiler and revert commit\ncategory: ops\ninputs_min: []\ncost_hint: low",
      "text": ""
    },
    {

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 80% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.struct.json (reported line 5)May include surrounding context.

json

"headings": [
    {
      "level": 2,
      "name": "name: skill-compiler\ndescription: Compile SKILL.md files into runtime artifacts (SKILL.struct.json and SKILL.toon), verify freshness/health, and prepare portable publish-ready skill folders for ClawHub-style registries.\ncontract_version: v0\nquick_cmd: skills/public/skill-compiler/scripts/compile-skill --skill skills/todoist/SKILL.md\nrisk_level: safe\ncapabilities:\nbins: [bash, mdquery, jq, toon]\nnetwork: false\nsecrets: []\ndry_run_cmd: skills/public/skill-compiler/scripts/check-env\ncompat:\nos: [linux, macos]\narch: [x64, arm64]\nshell: [bash]\nowner: matt\nlast_tested: 2026-03-08\nrollback: remove skills/public/skill-compiler and revert commit\ncategory: ops\ninputs_min: []\ncost_hint: low",
      "text": ""
    },
    {

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 80% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.struct.json (reported line 16)May include surrounding context.

json

"headings": [
    {
      "level": 2,
      "name": "name: skill-compiler\ndescription: Compile SKILL.md files into runtime artifacts (SKILL.struct.json and SKILL.toon), verify freshness/health, and prepare portable publish-ready skill folders for ClawHub-style registries.\ncontract_version: v0\nquick_cmd: skills/public/skill-compiler/scripts/compile-skill --skill skills/todoist/SKILL.md\nrisk_level: safe\ncapabilities:\nbins: [bash, mdquery, jq, toon]\nnetwork: false\nsecrets: []\ndry_run_cmd: skills/public/skill-compiler/scripts/check-env\ncompat:\nos: [linux, macos]\narch: [x64, arm64]\nshell: [bash]\nowner: matt\nlast_tested: 2026-03-08\nrollback: remove skills/public/skill-compiler and revert commit\ncategory: ops\ninputs_min: []\ncost_hint: low",
      "text": ""
    },
    {

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

This is a manifest/JSON-structured file, so vague-trigger review applies. The file presents preferred runtime trigger words as generic command phrases without negative examples or explicit limits on where they are recognized, which could overlap with ordinary instructions to execute something.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.