Reads TASKS.md and checks code_paths for implementation evidence. Detects phantom completions — tasks marked [x] but with no corresponding code. Writes VERIFICATION.md.
AI agents use sdd_verify_tasks to create or update resources in Specky — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Specky environment.
The tool performs a read/analysis operation (reading TASKS.md and checking code paths) but also writes a new file (VERIFICATION.md). Since it creates/modifies a file as its primary output, Write is the most appropriate category. The blast radius is medium — it writes a verification artifact but does not delete or execute code.
From the tool's definition Reads TASKS.md and checks code_paths for implementation evidence... Writes VERIFICATION.md
Documented attack patterns abuse exactly the kind of access sdd_verify_tasks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Specky, and nothing reaches the server without passing your rules. This is the rule we recommend for sdd_verify_tasks:
{
"version": "1",
"default": "deny",
"tools": {
"sdd_verify_tasks": {
"limits": [
{
"counter": "sdd_verify_tasks_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}sdd_verify_tasks stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Reads TASKS.md and checks code_paths for implementation evidence. Detects phantom completions — tasks marked [x] but with no corresponding code. Writes VERIFICATION.md. It is categorised as a Write tool in the Specky MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Specky MCP server in PolicyLayer and add a rule for sdd_verify_tasks: 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 Specky. Nothing to install.
sdd_verify_tasks 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 sdd_verify_tasks 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 sdd_verify_tasks. 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.
sdd_verify_tasks is provided by the Specky MCP server (paulasilvatech/specky). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Specky, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
56 Specky tools catalogued and risk-classified — across an index of 43,000+ MCP servers.