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 explore-framework-coveragegit 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/explore-framework-coverage)<a href="https://agentmods.dev/skills/cosai-oasis/secure-ai-tooling/explore-framework-coverage"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/explore-framework-coverage/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cosai-oasis/secure-ai-tooling/explore-framework-coverage"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/explore-framework-coverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00151 | $0.00843 |
| Opus 5.5 | $0.00060 | $0.00337 |
| Sonnet 5.5 | $0.00030 | $0.00169 |
| Haiku 4.5 | $0.00015 | $0.00084 |
Grade A, and why
explore-framework-coverage 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 15d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore: Framework Coverage
Given an external-framework entry, list the CoSAI Risk Map entities mapped to it — a read-only reverse index over the mappings. Consumer sibling of audit-framework-mappings (which audits mapping quality); reuse its knowledge of which frameworks apply to which entity types — don't duplicate its format rules.
Audience and voice
Compliance/audit and architects, who may not know CoSAI internals. Explain the framework entry briefly; link entity ids.
How to answer
- Identify the framework and entry. Resolve which framework and the specific entry the reader means.
- Know where it can appear. Consult the Framework Applicability table in
risk-map/docs/contributing/framework-mappings-style-guide.md— do not restate it from memory, it changes when a framework is registered or its scope revised. Only search the entity types where the framework actually applies. - Search the corpus mappings for the value. Values are version-pinned (ADR-027) — search the pinned form, e.g.
Article 14@2024,[email protected],[email protected],LLM06:2025,Tampering,AI Producer@2022. Grep themappingsblocks inrisk-map/yaml/{risks,controls,personas}.yaml. - Report coverage. The entities mapped to it (ids + titles), grouped by entity type; a one-line note of what the framework entry is; and any coverage gap ("no controls currently map to this" — a real and useful finding for an auditor).
- Link ids; adaptive output.
Output (adaptive)
- "what maps to X" → table:
Entity (id — title)| type | brief role. - coverage question → the list + an explicit gap note if the count is low/zero.
- unknown/ambiguous entry → confirm the framework + entry (and that the framework applies to some entity type), then answer.
- Always link ids; note this reflects the current corpus.
Boundaries
- Read-only, and coverage-only. You search for a framework value and report what maps to it. Judging whether a mapping is correctly formatted or version-pinned, or checking/fixing a mapping's correctness, is
audit-framework-mappings's job, not yours — redirect such questions there rather than answering them, and never perform or restate format/version-pinning rules yourself (that is the driftaudit-framework-mappingsand the style guide own). To select mappings while authoring usemapping-selection. - Report only what is in the corpus; flag gaps — do not author or infer mappings that aren't there.
- Consumer sibling of
audit-framework-mappings— reuse its applicability knowledge; don't restate its format rules.
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.
- 15d ago First seen · 39 lines · 151 tokens per session scan A f94c23018c6c
explore-framework-coverage is a skill published in the GitHub repository cosai-oasis/secure-ai-tooling (100 stars, last pushed today), licensed Apache-2.0. It adds 151 tokens to every session and 843 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-01.
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…
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.
web-sqli
SQL injection detection→exploitation→proof for web apps and APIs. Use when a parameter reaches a DB query, when input triggers a SQL error / boolean or time differential, or during VULN-ASSESSMENT/EXPLOITATION on a web target. Triggers - sql syntax error, ORA-/MySQL/psql/SQLite error string, ' or 1=1, order by…