AI-powered analysis of recon data for: $ARGUMENTS
Process
- Read all recon data:
ls recon/ and read key files
- Read brain data:
uv run python3 ../../tools/brain.py brief $ARGUMENTS
- Read tech stack intel:
uv run python3 ../../tools/intel_engine.py suggest <detected-stack>
- Read hacktivity patterns:
uv run python3 ../../tools/intel_engine.py analyze
Analysis Tasks (do all of these)
Crown Jewel Mapping
What's the most valuable thing an attacker could access on this target?
- Financial data? → hunt IDOR on payment/billing endpoints
- User PII? → hunt IDOR on profile/export endpoints
- Admin access? → hunt auth bypass on admin endpoints
- Infrastructure? → hunt SSRF → cloud metadata
Attack Path Ranking
Given the tech stack and recon output, rank the top 5 attack paths by:
- Likelihood of vulnerability existing (based on tech stack patterns)
- Impact if exploited (based on endpoint function)
- Competition (based on hacktivity — avoid heavily-reported vuln classes)
- Your past success (from brain patterns)
Blind Spot Detection
What has NOT been tested? What endpoints have no brain data?
Cross-reference recon output against brain tested endpoints.
Flag untested high-value endpoints.
Output
ANALYSIS: target.com
═════════════════════
Crown Jewels: [what's most valuable]
Top 5 Attack Paths:
1. [endpoint] × [vuln class] — likelihood: HIGH, impact: CRITICAL
2. ...
Blind Spots (untested P1 surface):
- /api/v2/payments/* — NO DATA in brain
- /api/v2/admin/* — NO DATA in brain
Recommendation: /hunt target.com --vuln-class [best bet]
Top-Tier Operator Addendum
Treat /analyze as a thesis generator, not a summary command. The output must make the next hour of hunting obvious.
- Build a weighted table before recommending anything:
asset_value: revenue, PII, admin, secrets, infrastructure, tenant boundaryexploit_likelihood: stack age, exposed methods, auth complexity, parser surface, prior bug class fitnovelty: low hacktivity overlap, new endpoint, changed JS, unusual integration, weak vendor patternproof_path: exact request needed to prove impact, required accounts, required evidence artifactpolicy_friction: rate limits, forbidden data access, third-party scope, credential validation rules
- Prefer attack paths with a short proof path over impressive theory. A boring IDOR with two accounts and a readback beats a speculative SSRF with no egress signal.
- Include negative evidence. If
/api/admin/* looks valuable but all routes are 403 with no differential, say that and explain what would change the ranking.
- Separate
P1 now, P2 if time, and Kill for this session. Top-tier analysis saves time by deleting tempting dead ends.
- Every recommendation must name the next command and the exact first test:
/hunt target --vuln-class idor plus the endpoint pair, account pair, and field to compare.
1---2name: analyze-43description: Analyze recon output with AI to suggest high-value targets and attack strategies. Usage: /analyze <target>4---5AI-powered analysis of recon data for: $ARGUMENTS67## Process81. Read all recon data: `ls recon/` and read key files92. Read brain data: `uv run python3 ../../tools/brain.py brief $ARGUMENTS`103. Read tech stack intel: `uv run python3 ../../tools/intel_engine.py suggest <detected-stack>`114. Read hacktivity patterns: `uv run python3 ../../tools/intel_engine.py analyze`1213## Analysis Tasks (do all of these)1415### Crown Jewel Mapping16What's the most valuable thing an attacker could access on this target?17- Financial data? → hunt IDOR on payment/billing endpoints18- User PII? → hunt IDOR on profile/export endpoints19- Admin access? → hunt auth bypass on admin endpoints20- Infrastructure? → hunt SSRF → cloud metadata2122### Attack Path Ranking23Given the tech stack and recon output, rank the top 5 attack paths by:241. Likelihood of vulnerability existing (based on tech stack patterns)252. Impact if exploited (based on endpoint function)263. Competition (based on hacktivity — avoid heavily-reported vuln classes)274. Your past success (from brain patterns)2829### Blind Spot Detection30What has NOT been tested? What endpoints have no brain data?31Cross-reference recon output against brain tested endpoints.32Flag untested high-value endpoints.3334### Output35```36ANALYSIS: target.com37═════════════════════3839Crown Jewels: [what's most valuable]4041Top 5 Attack Paths:421. [endpoint] × [vuln class] — likelihood: HIGH, impact: CRITICAL432. ...4445Blind Spots (untested P1 surface):46- /api/v2/payments/* — NO DATA in brain47- /api/v2/admin/* — NO DATA in brain4849Recommendation: /hunt target.com --vuln-class [best bet]50```5152## Top-Tier Operator Addendum5354Treat `/analyze` as a thesis generator, not a summary command. The output must make the next hour of hunting obvious.55561. Build a weighted table before recommending anything:57 - `asset_value`: revenue, PII, admin, secrets, infrastructure, tenant boundary58 - `exploit_likelihood`: stack age, exposed methods, auth complexity, parser surface, prior bug class fit59 - `novelty`: low hacktivity overlap, new endpoint, changed JS, unusual integration, weak vendor pattern60 - `proof_path`: exact request needed to prove impact, required accounts, required evidence artifact61 - `policy_friction`: rate limits, forbidden data access, third-party scope, credential validation rules622. Prefer attack paths with a short proof path over impressive theory. A boring IDOR with two accounts and a readback beats a speculative SSRF with no egress signal.633. Include negative evidence. If `/api/admin/*` looks valuable but all routes are 403 with no differential, say that and explain what would change the ranking.644. Separate `P1 now`, `P2 if time`, and `Kill for this session`. Top-tier analysis saves time by deleting tempting dead ends.655. Every recommendation must name the next command and the exact first test: `/hunt target --vuln-class idor` plus the endpoint pair, account pair, and field to compare.
h-mmer