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-risks-by-activitygit 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-risks-by-activity)<a href="https://agentmods.dev/skills/cosai-oasis/secure-ai-tooling/explore-risks-by-activity"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/explore-risks-by-activity/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-risks-by-activity"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/explore-risks-by-activity.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 | $0.00214 | $0.01101 |
| Opus 5.5 | $0.00086 | $0.00440 |
| Sonnet 5.5 | $0.00043 | $0.00220 |
| Haiku 4.5 | $0.00021 | $0.00110 |
Grade A, and why
explore-risks-by-activity 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 13d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore Risks by Activity
Help someone new to the CoSAI Risk Map find the risks relevant to what they actually do with AI — and what they can do about them. Read-only: you explain the framework's content, you never change it.
Audience and voice
The reader is security-literate but new to this framework. Explain framework terms the first time you use them (persona, risk, control, and the impacted-vs-implementer model) — do not assume they know the corpus. Always name and link the specific entity ids (riskX, controlY) so they can go deeper. Plain language over jargon.
How to answer
- Understand the activity/role. What does the reader do with AI — build, use, host, or govern it? Agents, models, or applications? At which point in the lifecycle? Restate it back briefly.
- Locate their persona(s). The framework's personas are roles defined by activity-based
identificationQuestionsinrisk-map/yaml/personas.yaml. Match the activity to the persona(s) whose questions it answers (e.g. "I build agent tool integrations" → Agentic Platform and Framework Providers; "I use an AI assistant" → AI System Users). Tell the reader which persona(s) they map to and what that means. (Explain: a persona is a role across the AI lifecycle.) - Find the risks that affect them. In
risk-map/yaml/risks.yaml, each risk lists the personas it impacts — the parties who bear the consequences. Surface the risks that list the reader's persona(s) as impacted. Also include risks whose scope (description,lifecycleStage,actorAccess, agentic vs non-agentic) clearly fits the activity even if the persona bridge misses them. (Explain: a risk's personas = who is harmed if it materializes.) - Attach the controls. For each surfaced risk, list the controls that address it — the risk's
controlsfield. These controls address the risk; use each control'spersonasfield to explain who implements it and what the reader can do. (Explain: a control is a defensive measure; its personas are its implementers, which can differ from the personas the risk impacts.) - Explain and prioritize. For each risk give: its id + title, a one-line plain-language "why this applies to you", and its addressing controls (ids + titles). Lead with the risks most specific to the stated activity.
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.
- 13d ago Changed 2584b3aa9eda
- 15d ago First seen · 41 lines · 214 tokens per session scan A 847e9b7b3ba2
explore-risks-by-activity is a skill published in the GitHub repository cosai-oasis/secure-ai-tooling (100 stars, last pushed today), licensed Apache-2.0. It adds 214 tokens to every session and 1,101 once invoked, about $0.0009 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…