feat: security analysis guidelines

[iamsreec]

Summary

Adds the guidelines-security-analysis skill: a 4-step pipeline (architecture analysis -> policy guidance questionnaire -> threat model -> enforcement mapping) that turns a target MCP server's source and OWASP Top 10 for Agentic AI Security (ASI01–ASI10) catalog into a scoped set of security guidelines for OPA policy.

Closes: #issue-number

Changes

• opa_policy/guidelines-security-analysis/guidelines-security-analysis.md — new orchestrator doc that sequences the 4 steps
• opa_policy/guidelines-security-analysis/owasp/architecture_analysis.md — maps an MCP server's layers, trust boundaries, and OPA enforcement points into architecture.md
• opa_policy/guidelines-security-analysis/owasp/policy_guidance_questionnaire.md — derives a 22-question policy-intent questionnaire from architecture.md + guidance.txt/system_vars.json/tool_definitions.json where present
• opa_policy/guidelines-security-analysis/owasp/threat_model.md — evaluates all 10 ASI categories against the tool using a three-question applicability test, sourced live from the catalog rather than hardcoded
• opa_policy/guidelines-security-analysis/owasp/enforcement_mapping.md — maps each threat instance to an enforcement layer (OPA vs. agent/tool/infra) and produces plain-English policy-rule requirements grounded in the catalog's mitigations
• src/smith/data/owasp_10_ai_catalog.json — new repo-relative data file: the OWASP Top 10 for Agentic AI Security catalog (ASI01–ASI10), single source of truth for category names, descriptions, impact, mitigations, and attack scenarios

All four step docs share a consistent "Authoritative Paths" contract: inputs are read from ONLY the named files under <TARGET_AGENT_PATH>/smith/guidelines-security-analysis/ (or the repo-relative catalog path), with an explicit stop-and-ask instruction if a required file is missing.

Checks

• make ci passes (lint, Rego lint, license headers, build smoke)
• make test passes (policy scorecard — needed if policy behavior changed) — not applicable, no assets/policy.rego changes in this PR
• CHANGELOG.md updated under ## [Unreleased] (if user-facing)
• Commits are signed off for the DCO (git commit -s) — verified via git log -1 --format='%B', Signed-off-by present

Notes (optional)

Base branch should be hl/promptfoo_config_auto, not main — this skill was built on top of unreleased work already on that branch. Confirmed clean: git diff --stat hl/promptfoo_config_auto..feat/guidelines-security-analysis shows exactly these 6 files (1392 insertions, 0 deletions), no policy_build/CLI/example files leaking in.

[araujof]

LGTM

[araujof]

Nice work!

Can you please make the following changes before merging?

• opa_policy/guidelines-security-analysis/steps/enforcement_mapping.md:42: Smith uses input.args.*, not input.arguments.*. Using the wrong path here could produce rules for fields that do not exist. Please update the workflow for consistency.

• opa_policy/guidelines-security-analysis/steps/enforcement_mapping.md:319: Step 8 assumes guidance contains numbered rules, but most bundled examples use headings and bullets. Since Step E overwrites guidance.txt, this could potentially discard user-written context. What if we preserved the original file and appended only missing rules?

• opa_policy/guidelines-security-analysis/guidelines-security-analysis.md:149: This says to include non-OPA gaps in guidance_updated.txt, while Step 8 explicitly forbids it. Please choose one behavior; keeping those gaps only in owasp_policy_guidelines.md seems safest.

[iamsreec]

Updated based on the comments.

[araujof]

Updated based on the comments.

Thanks! I just checked, and it looks like some of the issues have some residuals:

• Guidance preservation: Step E now appends, but SKILL.md still says to overwrite, Step 8 still assumes numbered rules, and bundled guidance_updated.txt examples still contain full replacements.

• Gap-register conflict: fixed in the core workflow, but the root and example READMEs still say non-OPA findings are added to guidance_updated.txt.