attack-vector-generation
This Claude Code skill generates specific, executable attack vectors targeting identified threat surfaces by spawning a specialized subagent for adversarial ideation. Use it during security research and penetration testing workflows when you need concrete attack strategies tailored to particular vulnerabilities, with outputs ranked by impact severity and conditions for escalation.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/attack-vector-generation && cp -r /tmp/attack-vector-generation/skills/attack-vector-generation ~/.claude/skills/attack-vector-generationSKILL.md
# Attack Vector Generation Generates concrete, executable attack vectors targeting a specific threat surface. ## Execution Subagent — spawned via subagent-spawning/spawn-agent. ## Why Subagent Vector generation requires creative adversarial thinking without defensive contamination. Each surface needs fresh attack ideation. ## Input - **surface**: The specific threat surface to target (from threat-surface-mapping) - **artifact**: The artifact being attacked - **prior_findings**: Results from previous probes (to avoid repetition) ## Output - **vectors**: List of specific attack vectors with description, expected outcome, and severity estimate - **priority_order**: Recommended execution order (highest-impact first) - **follow_up_triggers**: Conditions that should trigger deeper investigation <!-- BEGIN available-tables (generated) --> ## Available SOPs Optional, no fixed order; the final leaf is always a sop. | SOP | When to use | | --- | --- | | spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. | <!-- END available-tables (generated) -->
Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.
Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.
loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.
loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.
Strategy: Inference to the best explanation in the face of anomalies
Remove components one by one, observe system changes to reveal hidden
Map system architecture to ablatable units for ablation studies
Design ablation studies to isolate component contributions in ML systems