Batch-score multiple npm, PyPI, Cargo, or Go packages for supply chain risk. Takes a list of package names and returns a risk table sorted by commitment score (lowest = highest risk first). Risk flags: - CRITICAL: single publisher + >10M weekly downloads (publish-access concentration risk) - HIGH...
Part of the Commit — Supply Chain Risk Scoring server.
Free to start. No card required.
AI agents use audit_dependencies to create or modify resources in Commit — Supply Chain Risk Scoring. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call audit_dependencies repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Commit — Supply Chain Risk Scoring.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"audit_dependencies": {
"limits": [
{
"counter": "audit_dependencies_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Commit — Supply Chain Risk Scoring policy for all 11 tools.
These attack patterns abuse exactly the kind of access audit_dependencies gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Batch-score multiple npm, PyPI, Cargo, or Go packages for supply chain risk. Takes a list of package names and returns a risk table sorted by commitment score (lowest = highest risk first). Risk flags: - CRITICAL: single publisher + >10M weekly downloads (publish-access concentration risk) - HIGH: new package (<1yr) + high downloads (unproven, rapid adoption = supply chain risk) - WARN: low publisher count + high downloads Perfect for auditing a full package.json, requirements.txt, Cargo.toml, or go.mod — paste your dependency list and get a prioritized risk report. For Go: pass full module paths (e.g., "github.com/gin-gonic/gin", "golang.org/x/net") and set ecosystem="golang". The "maintainers" column shows GitHub contributor count since Go has no centralized publisher concept. Examples: score all deps in a project, compare two similar packages, identify abandonware before it becomes a CVE.. It is categorised as a Write tool in the Commit — Supply Chain Risk Scoring MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Commit — Supply Chain Risk Scoring MCP server in PolicyLayer and add a rule for audit_dependencies: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Commit — Supply Chain Risk Scoring. Nothing to install.
audit_dependencies is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the audit_dependencies rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for audit_dependencies. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
audit_dependencies is provided by the Commit — Supply Chain Risk Scoring MCP server (proof-of-commitment). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Commit — Supply Chain Risk Scoring tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.