High-risk tools in SpecLock - AI Constraint Engine
4 of the 44 tools in SpecLock - AI Constraint Engine are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
speclock_build_graphExecute 3/5Build/refresh code dependency graph from imports (JS/TS/Python).
-
speclock_compile_specExecute 3/5Compile natural language (PRDs, READMEs) into structured constraints via Gemini Flash.
-
speclock_parse_diffExecute 3/5Parse unified diff into structured changes — imports, exports, symbols, routes, schema detection.
-
speclock_session_briefingExecute 3/5Start a new session and get a full briefing.
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.
More on SpecLock - AI Constraint Engine
Enforce policy on SpecLock - AI Constraint Engine
One command generates a policy scaffold for every server in your MCP config.
npx -y @policylayer/intercept init