AgentAegis

scan_skill

Assess an agent skill for supply-chain risks including prompt injection, over-broad permissions, and hidden threats. Receive a PROCEED, CAUTION, or BLOCK verdict.

Instructions

Scan an agent SKILL (git repo or SKILL.md) for supply-chain risk BEFORE trusting it — prompt-injection / hidden-unicode in the instructions (hard block), over-broad allowed-tools grants, plus exfiltration, dangerous capabilities, secrets and obfuscation in bundled scripts → a PROCEED/CAUTION/BLOCK verdict.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "source": "<source>"
    },
    "name": "scan_skill"
  }
}

Input Schema

Name	Required	Description	Default
`source`	Yes
`previous_scan_id`	No	Optional. A prior scan_id (from agent_history) to record as this call's parent — builds a traversable chained-workflow lineage retrievable via agent_scan_get. Must be one of your own scans; ignored otherwise. Does not change this tool's analysis.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Jun 26, 2026

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses the scan's inputs (git repo or SKILL.md) and the verdict output, and lists several risk categories. However, it does not mention whether the tool makes external network calls, modifies anything, or its authentication requirements, leaving some behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence using an em dash and arrow to convey purpose, target, risks, and outcome. Every phrase is informative and necessary, with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description adequately explains the output verdict (PROCEED/CAUTION/BLOCK). It covers the main input types and risk categories. Minor gap: it doesn't specify if the verdict is the only output or if there is a detailed report, but it is largely sufficient for a scanning tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%. The description adds clarity by associating 'git repo' and 'SKILL.md' with the source type enum, but does not further elaborate on the source object's structure (url, skill_md) beyond the schema. The previous_scan_id parameter has a detailed schema description, so the description provides no extra value there.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool scans an agent SKILL for supply-chain risk and provides a PROCEED/CAUTION/BLOCK verdict. It mentions specific checks (prompt-injection, hidden-unicode, over-broad grants, etc.), making it distinct from sibling security tools like sast_scan or secret_scan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'BEFORE trusting it' gives a clear usage context. The description lists specific risks checked, implying when to use. However, it does not explicitly state when not to use or provide alternatives among siblings, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.