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 BagelHole/DevOps-Security-Agent-Skills --skill saas-security-posturegit clone --depth 1 https://github.com/BagelHole/DevOps-Security-Agent-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/bagelhole/devops-security-agent-skills/saas-security-posture)<a href="https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/saas-security-posture"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/saas-security-posture/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/bagelhole/devops-security-agent-skills/saas-security-posture"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/saas-security-posture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 113 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 250 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 128 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 251 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 319 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00054 | $0.03786 |
| Opus 5 | $0.00027 | $0.01893 |
| Sonnet 5 | $0.00011 | $0.00757 |
| Haiku 4.5 | $0.00005 | $0.00379 |
Grade A, and why
saas-security-posture scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer ${SLACK_ADMIN_TOKEN}" \ How it starts
The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SaaS Security Posture Management for Startups
Secure every SaaS tool your company relies on with practical, command-driven hardening.
1. When to Use This Skill
- SOC 2 preparation — auditors need evidence of MFA, access controls, and OAuth governance.
- Suspicious OAuth app — an employee authorized a third-party app with broad scopes.
- SaaS sprawl — teams sign up for tools with company email and nobody tracks them.
- Post-incident hardening — after phishing or credential leaks, tighten every surface.
2. SaaS Inventory Audit
Google Workspace — OAuth Grants
gam all users show tokens > oauth_tokens_audit.csv
GitHub — Installed Apps
gh api /orgs/{ORG}/installations --paginate \
--jq '.installations[] | {app: .app_slug, permissions: .permissions, created: .created_at}'
gh api /orgs/{ORG}/credential-authorizations --paginate \
--jq '.[] | {login: .login, credential_type: .credential_type}'
Slack — Approved and Pending Apps
curl -s -H "Authorization: Bearer ${SLACK_ADMIN_TOKEN}" \
"https://slack.com/api/admin.apps.approved.list" | jq '.approved_apps[] | {name: .app.name, id: .app.id}'
curl -s -H "Authorization: Bearer ${SLACK_ADMIN_TOKEN}" \
"https://slack.com/api/admin.apps.requests.list" | jq '.app_requests[]'
AWS — IAM Credential Report
aws iam generate-credential-report
aws iam get-credential-report --output text --query 'Content' | base64 -d > iam_credential_report.csv
Master Inventory Template
tools:
- name: Google Workspace
owner: [email protected]
sso: true
mfa: enforced
- name: GitHub Enterprise
owner: [email protected]
sso: true
mfa: enforced
- name: Slack Business+
owner: [email protected]
sso: true
app_approval: required
- name: AWS Organizations
owner: [email protected]
sso: true
scp_enforced: true
3. GitHub Security Hardening
# Enforce 2FA and find non-compliant members
gh api -X PATCH /orgs/{ORG} -f two_factor_requirement_enabled=true
gh api /orgs/{ORG}/members?filter=2fa_disabled --paginate --jq '.[].login'
# Verify SAML SSO identities
gh api /orgs/{ORG}/credential-authorizations --paginate \
--jq '.[] | {login: .login, saml_name_id: .saml_name_id}'
# Add IP allow list entry
gh api -X POST /orgs/{ORG}/ip-allow-list \
-f allow_list_value="203.0.113.0/24" -f name="Office VPN" -F is_active=true
# Branch protection on main
gh api -X PUT /repos/{ORG}/{REPO}/branches/main/protection \
-H "Accept: application/vnd.github+json" --input - <<'EOF'
{
"required_status_checks": {"strict": true, "contexts": ["ci/build","ci/test"]},
"enforce_admins": true,
"required_pull_request_reviews": {
"required_approving_review_count": 2,
"dismiss_stale_reviews": true,
"require_code_owner_reviews": true
},
"restrictions": null,
"allow_force_pushes": false,
"allow_deletions": false
}
EOF
# Audit PATs and revoke stale tokens
gh api /orgs/{ORG}/personal-access-tokens --paginate \
--jq '.[] | {owner: .owner.login, name: .token_name, expires: .token_expires_at}'
gh api -X DELETE /orgs/{ORG}/personal-access-tokens/{PAT_ID}
# Audit deploy keys and webhooks
for repo in $(gh repo list {ORG} --limit 500 --json name -q '.[].name'); do
gh api /repos/{ORG}/${repo}/keys --jq '.[] | {title: .title, read_only: .read_only}'
done
gh api /orgs/{ORG}/hooks --jq '.[] | {url: .config.url, events: .events, active: .active}'
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.
- 7d ago First seen · 401 lines · 54 tokens per session scan A 2ace361c76c9
saas-security-posture is a skill published in the GitHub repository BagelHole/DevOps-Security-Agent-Skills (1,071 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 3,786 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
implementing-aws-config-rules-for-compliance
Implementing AWS Config rules for continuous compliance monitoring of AWS resources, deploying managed and custom rules aligned to CIS and PCI DSS frameworks, configuring automatic remediation with SSM Automation, and aggregating compliance data across accounts.
ec2
AWS EC2 virtual machine management — instances, security groups, key pairs, AMIs, EBS volumes, Auto Scaling Groups, Spot Instances, Session Manager, placement groups, and instance lifecycle automation. Trigger on ANY of these, even when EC2 isn't named explicitly: - Launching or provisioning: "spin up a server"…
eventbridge
AWS EventBridge serverless event bus for event-driven architectures. Use when creating rules, configuring event patterns, setting up scheduled events, integrating with SaaS, or building cross-account event routing.
s3
AWS S3 object storage for bucket management, object operations, and access control. Use when creating buckets, uploading files, configuring lifecycle policies, setting up static websites, managing permissions, or implementing cross-region replication.
sqs
AWS SQS message queue service for decoupled architectures. Use when creating queues, configuring dead-letter queues, managing visibility timeouts, implementing FIFO ordering, or integrating with Lambda.
iam
AWS Identity and Access Management for users, roles, policies, and permissions. Use when creating IAM policies, configuring cross-account access, setting up service roles, troubleshooting permission errors, or managing access control.