Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cosai-oasis/secure-ai-tooling --skill audit-framework-mappingsgit clone --depth 1 https://github.com/cosai-oasis/secure-ai-toolingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cosai-oasis/secure-ai-tooling/audit-framework-mappings)<a href="https://agentmods.dev/skills/cosai-oasis/secure-ai-tooling/audit-framework-mappings"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/audit-framework-mappings.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.04376 |
| Opus 5 | $0.00032 | $0.02188 |
| Sonnet 5 | $0.00013 | $0.00875 |
| Haiku 4.5 | $0.00006 | $0.00438 |
Grade A, and why
audit-framework-mappings scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framework Mappings Audit
Audit framework mappings for correctness, style compliance, and term validity.
Scope
Three modes, chosen by what the caller provides — each is a first-class mode, not a side effect of another:
- Single entity: a specific entity id already in the corpus (e.g.,
riskModelEvasion,controlInputValidationAndSanitization,personaEndUser). Audit that entity's existing mappings, or a new value being proposed for addition to that entity. Both are single-entity scope: the entity already exists, so this is distinct from candidate mode below, which is for an entity that does not exist yet. - Whole corpus (the default): every entity across
risks.yaml,controls.yaml,personas.yaml. - Candidate value(s) for an entity not yet in the corpus (pre-PR authoring): audit the given value(s) directly. No corpus id lookup applies — the entity doesn't exist yet, so there is nothing to look up by id. The caller must also state the entity type the candidate targets (risk, control, or persona), since parts of the checklist (e.g., MITRE ATLAS technique-vs-mitigation) depend on it. See Candidate mode checklist.
Reference documents
Read these before auditing:
- Style guide (authoritative):
risk-map/docs/contributing/framework-mappings-style-guide.md
Audit checklist (for whole-corpus and single-entity scope)
For each entity with mappings, verify ALL of the following. Report pass/fail per item. Candidate mode (an entity not yet in the corpus) does not have "mappings" on an entity to iterate over — it uses its own Candidate mode checklist below instead.
Format and version compliance
Mapping values are version-pinned (ADR-027): every value carries its framework's version token, except STRIDE, which is intentionally unversioned. Verify each value against the canonical pinned pattern for its framework in the authoritative style guide (risk-map/docs/contributing/framework-mappings-style-guide.md, "Identifier Enforcement" table) — read the patterns from the guide every time; do not restate them from memory or inline here. The guide is the single source for pattern and version-token conventions across every supported framework, including any framework registered after this skill was written — new frameworks are a recurring, actively-requested change (see open issues against frameworks.yaml), so nothing about the pinned-pattern set may live in two places.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · +2 lines 130f26565972
- 8d ago First seen · 87 lines · 65 tokens per session scan A b64890a1ff57
audit-framework-mappings is a skill published in the GitHub repository cosai-oasis/secure-ai-tooling (98 stars, last pushed yesterday), licensed Apache-2.0. It adds 65 tokens to every session and 4,376 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
svc-mobile-android
Android APK static analysis — OWASP Mobile Top 10, Retrofit API audit, transport security, smali reading, component export, auth flow analysis. Use when target is an APK/Android app. Triggers - APK, Android, mobile app, decompiled, smali, jadx, apktool.
svc-pivoting
Turn a foothold into a RELIABLE pivot (SOCKS tunnel + persistent shell) so internal volume never rides a fragile stateless RCE. Use the moment you have code-exec on a dual-homed/edge host and need to reach an internal segment. Triggers - dual-homed host, "not reachable from my box", internal CIDR behind a foothold…
reporting-phase
Reporting phase — generate structured pentest report from findings. Use when the current phase is REPORTING.
web-auth-bypass-idor
Broken access control - IDOR, privilege escalation, JWT abuse, mass assignment, forced browsing - for web apps and APIs. Use on any multi-user or role-based app with object IDs, tokens, or admin functionality. Triggers - /api/users/ , /orders/ , ?account=/uid=/doc=, JWT (eyJ...), role/isAdmin field, admin panel, "403…
web-deserialization
Insecure deserialization to RCE for web apps. Use when the app deserializes attacker-controlled data - cookies/tokens/hidden fields/params that are serialized blobs, VIEWSTATE, Java/PHP/.NET/Python/Node apps. Triggers - base64 starting rO0AB or hex AC ED 00 05 (Java), PHP serialize O-prefix, VIEWSTATE, python pickle…
web-lfi-traversal
Path traversal / Local File Inclusion detection→file-read→RCE for web apps. Use when a param names a file/path/page/template/lang/download, or a response embeds file contents. Triggers - file=/page=/path=/template=/lang=/download=/include= param, ../, %2e%2e, "no such file", directory listing, download endpoint.