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 woohyun212/security-skill --skill web-vuln-saml-ssogit clone --depth 1 https://github.com/woohyun212/security-skillWrote 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/woohyun212/security-skill/web-vuln-saml-sso)<a href="https://agentmods.dev/skills/woohyun212/security-skill/web-vuln-saml-sso"><img src="https://agentmods.dev/badge/skills/woohyun212/security-skill/web-vuln-saml-sso/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/woohyun212/security-skill/web-vuln-saml-sso"><img src="https://agentmods.dev/badge/skills/woohyun212/security-skill/web-vuln-saml-sso.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 | $0.00022 | $0.01925 |
| Opus 5 | $0.00011 | $0.00962 |
| Sonnet 5 | $0.00004 | $0.00385 |
| Haiku 4.5 | $0.00002 | $0.00193 |
Grade B, and why
web-vuln-saml-sso scanned grade B with 2 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 11d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `xmllint` not found | libxml2-utils not installed | `sudo apt install libxml2-utils` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` must be installed How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What this skill does
Detects vulnerabilities in SAML-based Single Sign-On implementations by intercepting and manipulating SAML responses. Tests for XML Signature Wrapping (XSW variants XSW1–XSW8), signature removal/stripping, NameID comment injection, SAML replay attacks, XXE in SAML responses, and Assertion Consumer Service (ACS) URL manipulation.
When to use
- When auditing a web application that uses SAML 2.0 for authentication or federation
- When testing an Identity Provider (IdP) or Service Provider (SP) for SSO weaknesses
- When evaluating whether SAML signature validation can be bypassed to authenticate as an arbitrary user
- When checking for XML-level injection or replay vulnerabilities in SSO flows
Prerequisites
curlmust be installedbase64(GNU coreutils) must be availablexmllint(fromlibxml2-utils) must be installed for XML parsing:apt install libxml2-utils- Ability to intercept and replay SAML responses (browser proxy or captured assertion)
- A valid SAML response from a legitimate authentication flow
Inputs
| Variable | Description | Example |
|---|---|---|
ACS_URL |
Assertion Consumer Service URL (SP endpoint that receives SAML response) | https://sp.example.com/saml/acs |
SAML_RESPONSE_B64 |
Base64-encoded SAML response captured from a valid login | PHNhbWxwOl... |
TARGET_USER |
Username/email to impersonate in tests | [email protected] |
LEGITIMATE_USER |
Username of the account used to obtain the real assertion | [email protected] |
Workflow
Step 1: Identify SAML endpoints and decode the response
ACS_URL="https://sp.example.com/saml/acs"
SAML_RESPONSE_B64="PHNhbWxwOl..."
TARGET_USER="[email protected]"
LEGITIMATE_USER="[email protected]"
WORK_DIR=$(mktemp -d /tmp/saml_test_XXXXXX)
echo "[+] Working directory: $WORK_DIR"
# Decode and pretty-print the SAML response
echo "$SAML_RESPONSE_B64" | base64 -d > "$WORK_DIR/saml_original.xml"
xmllint --format "$WORK_DIR/saml_original.xml" > "$WORK_DIR/saml_pretty.xml" 2>/dev/null \
|| cp "$WORK_DIR/saml_original.xml" "$WORK_DIR/saml_pretty.xml"
echo "=== Step 1: SAML response structure ==="
grep -E "<(saml:|samlp:)?(Issuer|NameID|Conditions|AudienceRestriction|Audience|AuthnStatement|AttributeStatement|Signature)" \
"$WORK_DIR/saml_pretty.xml" | head -20
echo ""
echo "[+] NameID value:"
grep -oP '(?<=<saml:NameID[^>]*>)[^<]+' "$WORK_DIR/saml_pretty.xml" | head -3
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.
- 11d ago First seen · 179 lines · 22 tokens per session scan B 9a9cb3fae4fe
web-vuln-saml-sso is a skill published in the GitHub repository woohyun212/security-skill (21 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 1,925 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.