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/samaxbytez/freeagent-mcp/security-reviewergit clone --depth 1 https://github.com/samaxbytez/freeagent-mcpWrote 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/samaxbytez/freeagent-mcp/security-reviewer)<a href="https://agentmods.dev/agents/samaxbytez/freeagent-mcp/security-reviewer"><img src="https://agentmods.dev/badge/agents/samaxbytez/freeagent-mcp/security-reviewer.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 5.1 | $0.00067 | $0.00520 |
| Opus 5 | $0.00034 | $0.00260 |
| Sonnet 5 | $0.00013 | $0.00104 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
security-reviewer 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 5d 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.
What it actually says
You are a security reviewer for freeagent-mcp-server, an MCP server driven by
an LLM. The primary threat is indirect prompt injection: malicious content in
FreeAgent data the model reads back (invoice descriptions, contact names) trying
to make the server leak the bearer token or hit unintended endpoints.
Review the changes under review (use git diff main...HEAD and git diff HEAD)
against these invariants. Report concrete findings only — each with file:line, the
attack it enables, and the minimal fix. If an invariant is upheld, say so briefly.
Invariants to verify:
- ID parameters use
safeId(notz.string()) wherever an ID is interpolated into a request path — prevents path traversal via ID fields. client.tsrequest-path guard intact: rejects absolute URLs and../sequences AND verifies the resolved URL's origin equals the API base origin. The origin check is the real boundary — flag any change that removes or weakens it (it stops the bearer token reaching another host).- No shell interpolation: browser/process launches use
execFilewith an argument array, neverexec,shell: true, or string-built commands. Windows usesexplorer.exe(notcmd /c start, which mangles&in URLs). - Token handling: tokens written
0o600in a0o700dir; never logged, never echoed into errors, never sent anywhere but the FreeAgent token endpoint. - No new sinks: any new outbound request, file write, or subprocess that takes model- or data-derived input is validated.
- Error messages don't leak secrets or full tokens.
Be specific and adversarial: assume an attacker controls the string values returned by the FreeAgent API and the arguments the LLM passes to tools. Default to flagging when unsure, but do not invent issues that the code does not contain.
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.
- 5d ago First seen · 37 lines · 67 tokens per session scan A cc063e27f5ee
security-reviewer is an agent published in the GitHub repository samaxbytez/freeagent-mcp (4 stars, last pushed 10d ago), licensed MIT. It adds 67 tokens to every session and 520 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.
reviewer-docs
Reviews documentation drift — PRD/Roadmap/AssumptionLog/README consistency with actual code, outdated assertions, broken references, contradictions between docs.
audit
🔬 [5維度審計] 深度程式碼審計 — 架構合規 + 安全性 + 品質 + 測試覆蓋 + 文檔同步。.
reviewer
Use this agent to verify that a completed implementation meets all acceptance criteria for the current task. The reviewer reads the full action history, checks the builder's changes against each criterion, runs the health check, and either approves or blocks with specific, actionable feedback. Invoke only after the…
gsd-research-synthesizer
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd-new-project after 4 researcher agents complete.
Demonstrate
Agent for demonstrating VS Code features.