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 orcasecurity/orca-skills --skill orca-data-exposuregit clone --depth 1 https://github.com/orcasecurity/orca-skillsWrote 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/orcasecurity/orca-skills/orca-data-exposure)<a href="https://agentmods.dev/skills/orcasecurity/orca-skills/orca-data-exposure"><img src="https://agentmods.dev/badge/skills/orcasecurity/orca-skills/orca-data-exposure/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/orcasecurity/orca-skills/orca-data-exposure"><img src="https://agentmods.dev/badge/skills/orcasecurity/orca-skills/orca-data-exposure.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.04191 |
| Opus 5 | $0.00039 | $0.02096 |
| Sonnet 5 | $0.00016 | $0.00838 |
| Haiku 4.5 | $0.00008 | $0.00419 |
Grade A, and why
orca-data-exposure 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 9d 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 — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orca Data Exposure Skill
Answers the question: "Where is our sensitive data, is it protected, and what's at risk right now?"
Provides a DSPM (Data Security Posture Management) view: discovers sensitive data across the environment (secrets, PII, credentials, API keys, financial data), identifies unprotected or exposed data stores, ranks data risks by exposure level, and generates a remediation plan to secure the most critical data first.
Usage
/orca-data-exposure
/orca-data-exposure secrets
/orca-data-exposure account 123456789012
Or natural language:
- "where's our sensitive data?"
- "find exposed API keys"
- "what PII is at risk?"
- "data exposure report"
- "show me unprotected data stores"
- "DSPM summary"
Processing Logic
Step 1: Determine Scope
Parse user input:
- All data types: no argument → full DSPM view
- Specific type: "secrets" / "PII" / "credentials" / "API keys" → filter
- Account-specific: "account 123456789012" → filter by account
- Asset-specific: "data on bastion-admin" → filter by asset
Step 2: Gather Data (run ALL in parallel)
Run 6 discovery_search queries covering different data exposure categories:
Query 1: Exposed secrets and credentials
discovery_search:
search_phrase: "exposed secrets credentials API keys passwords"
limit: 10
Query 2: PII exposure
discovery_search:
search_phrase: "sensitive data PII personally identifiable information exposed"
limit: 10
Query 3: Unencrypted data stores
discovery_search:
search_phrase: "unencrypted S3 buckets databases storage with sensitive data"
limit: 10
Query 4: Public data stores with sensitive content
discovery_search:
search_phrase: "publicly accessible storage buckets with sensitive data or secrets"
limit: 10
Query 5: Sensitive data on internet-facing assets
discovery_search:
search_phrase: "internet facing assets with sensitive data or secrets"
limit: 10
Query 6: Certificate and key exposure
discovery_search:
search_phrase: "exposed private keys certificates TLS SSL"
limit: 10
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.
- 9d ago First seen · 506 lines · 79 tokens per session scan A e45370e08ec3
orca-data-exposure is a skill published in the GitHub repository orcasecurity/orca-skills (49 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 4,191 once invoked, about $0.0004 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
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
ddia-systems
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID…
database-patterns
DB schema design and query tuning: normalization, indexing, N+1, transactions, EXPLAIN. Triggers: schema, index, slow query, N+1, PostgreSQL, MySQL, EXPLAIN, deadlock, query plan.
migration-patterns
Zero-downtime DB migrations: expand-contract, double-write, backfill, blue-green. Triggers: migration, schema change, backfill, ALTER TABLE, online DDL.
migrate
Run/create DB migrations (Alembic, Prisma, Laravel, Django, Flyway, Drizzle); checks backup. Triggers: apply migration, rollback, generate migration.
managed-db-services
Configure DigitalOcean Managed MySQL, MongoDB, Valkey, Kafka, and OpenSearch for App Platform. Use when setting up non-PostgreSQL databases, configuring trusted sources, or troubleshooting database connectivity.