mantis-pipeline

Mantis runs a staged detect-then-validate pipeline. The core bet: detection is commodity, **validation precision is the product** -- "what survives attacker-simulation is real." Detect is generous (high recall, no self-censoring); Validate is ruthless (kill false positives with cited roadblocks). Establish scope and authorization FIRST. Work only on targets the user owns or is explicitly authorized to test. If authorization for active/exploit testing is unclear, restrict the run to read-only static analysis until scope is established. Never do destructive, persistence, exfiltration, DoS, or stealth actions. Pipeline, stage -> subagent (`spawn_agent` agent_type) -> tools: 1. Recon -> `recon` -> program-analysis (`source_sink_scan`, `ast_grep_scan`), read code. Output: ranked attack-surface map. 2. Context/Enrich -> `context-enrich` -> program-analysis, code retrieval. Output: per-sink context + reachability pre-classification. 3. Detect -> `detector` -> `semgrep_scan`, `codeql_analyze`, `osv_scan`, `trufflehog_scan`, `bandit_scan`, `trivy_scan` + LLM reasoning for classes scanners miss (IDOR, authz, logic, SSRF, deserialization, SSTI). Registers `candidate`s via `finding_create`. Do NOT self-censor here. 4. Reachability -> `reachability` -> `smt_check_reachability` (z3), taint tracing. `unsat` -> reject with the unsat as roadblock. 5. Validate -> `validator` -> attacker-simulation. Confirms (`finding_update` to `confirmed`, needs reachability evidence) or rejects (needs a s...