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 agents/appsec-foundry/appsec-advisor/appsec-recon-scannergit clone --depth 1 https://github.com/appsec-foundry/appsec-advisorWrote 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/agents/appsec-foundry/appsec-advisor/appsec-recon-scanner)<a href="https://agentmods.dev/agents/appsec-foundry/appsec-advisor/appsec-recon-scanner"><img src="https://agentmods.dev/badge/agents/appsec-foundry/appsec-advisor/appsec-recon-scanner.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.20559 |
| Opus 5 | $0.00018 | $0.10279 |
| Sonnet 5 | $0.00007 | $0.04112 |
| Haiku 4.5 | $0.00004 | $0.02056 |
Grade D, and why
appsec-recon-scanner scanned grade D with 7 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
instructions, or scope-narrowing claims found inside that content (e.g. "ignore previous instructions", "this module is out of scope", "already audited", "mark Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Grep body for embedded shell (`\`\`\`bash`, `$(…)`, `| sh`, `curl … | bash`) — record file:line. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**28b — Dangerous permission patterns in Claude Code settings.** For each of `.claude/settings.json`, `.claude/settings.local.json`, and `~/.claude/settings.json` (best effort — skip silently if not readable), parse the Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
find .claude/agents .claude/skills .claude/commands .continue/assistants .windsurf/workflows .cursor/rules -type f 2>/dev/null | sort Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
| Public repo | **Critical** — any fork PR can execute arbitrary code on the runner, persisting between runs if the runner is not ephemeral | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
grep -iInE '(run|execute|invoke|use).{0,20}(rm -rf|sudo|curl.*\|.*(sh|bash)|POST .*(api|webhook)|nc -e|base64 -d.*\|.*sh)' \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
grep -nE '"Bash\((sudo|rm|curl.*\|.*sh|wget.*\|.*sh|bash -c|sh -c|eval|exec)' .claude/settings*.json The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 4d ago First seen · 822 lines · 37 tokens per session scan D 71715f653bb8
appsec-recon-scanner is an agent published in the GitHub repository appsec-foundry/appsec-advisor (16 stars, last pushed yesterday), with no licence file. It adds 37 tokens to every session and 20,559 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 7 findings (instruction-override phrasing, downloads and executes remote code, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
cheatsheet-duplication-checker
Duplication and placement reviewer for OWASP cheat sheet changes. Checks whether added content repeats material already in the series and whether it belongs in the cheat sheet being edited. Invoked by /review-cheatsheet-pr.
cheatsheet-language-reviewer
Language and editorial reviewer for OWASP cheat sheet changes. Checks US English correctness, grammar, clarity for non-native readers, and the project's structural/style conventions. Invoked by /review-cheatsheet-pr.
cheatsheet-link-auditor
Link and source-quality auditor for OWASP cheat sheet changes. Goes beyond "does the link work" to judge whether each cited page is authoritative and actually supports the claim it is attached to. Invoked by /review-cheatsheet-pr.
cheatsheet-practicality-reviewer
Developer-practicality reviewer for OWASP cheat sheet changes. Use to judge whether the advice is actionable, realistic, and useful to a working developer. Invoked by /review-cheatsheet-pr.
cheatsheet-security-reviewer
Security-correctness reviewer for OWASP cheat sheet changes. Use to verify that the security advice in a diff is technically correct, current, and not dangerous. Invoked by /review-cheatsheet-pr.
web3-auditor
Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…