SkillAudit report — paypal/agent-toolkit

Scanned 2026-04-24 by SkillAudit v0.2 (static checks + LLM-assisted prompt-injection red-team).

Commit: b4da285 · Stars: 185 · Days since last push: 153

LLM prompt-injection probe: no-tool-surface

Overall grade: F (10/100)

Security findings

Production sources:

• HIGH python/paypal_agent_toolkit/shared/paypal_client.py:48 — HTTP client call with user-controlled argument 'token_url' — no URL allowlist / validation found in file

response = requests.post(

• HIGH python/paypal_agent_toolkit/shared/paypal_client.py:75 — HTTP client call with user-controlled argument 'url' — no URL allowlist / validation found in file

response = requests.post(url, headers=headers, json=payload)

• HIGH python/paypal_agent_toolkit/shared/paypal_client.py:103 — HTTP client call with user-controlled argument 'url' — no URL allowlist / validation found in file

response = requests.get(url, headers=headers)

• HIGH python/paypal_agent_toolkit/shared/paypal_client.py:127 — HTTP client call with user-controlled argument 'url' — no URL allowlist / validation found in file

response = requests.put(url, headers=headers, json=payload)

• HIGH typescript/src/shared/client.ts:86 — HTTP client call with user-controlled argument 'url' — no URL allowlist / validation found in file

const response = await axios.post(

• HIGH typescript/src/shared/functions.ts:62 — HTTP client call with user-controlled argument 'url' — no URL allowlist / validation found in file

const response = await axios.post(url, params, { headers });

• HIGH typescript/src/shared/functions.ts:119 — HTTP client call with user-controlled argument 'url' — no URL allowlist / validation found in file

const response = await axios.get(url, { headers, params });

• HIGH typescript/src/shared/functions.ts:144 — HTTP client call with user-controlled argument 'url' — no URL allowlist / validation found in file

const response = await axios.get(url, { headers });

• HIGH typescript/src/shared/functions.ts:177 — HTTP client call with user-controlled argument 'url' — no URL allowlist / validation found in file

const response = await axios.post(url, params, { headers });

• HIGH typescript/src/shared/functions.ts:207 — HTTP client call with user-controlled argument 'url' — no URL allowlist / validation found in file

const response = await axios.post(url, params, { headers });

Permissions

_No findings on this axis._

Credentials

Production sources:

• WARN .env.sample — .env file present in repo tree — verify it's a template, not real secrets

.env.sample

• WARN python/examples/bedrock/.env.sample — .env file present in repo tree — verify it's a template, not real secrets

python/examples/bedrock/.env.sample

• WARN python/examples/crewai/.env.sample — .env file present in repo tree — verify it's a template, not real secrets

python/examples/crewai/.env.sample

• WARN python/examples/langchain/.env.sample — .env file present in repo tree — verify it's a template, not real secrets

python/examples/langchain/.env.sample

• WARN python/examples/openai/.env.sample — .env file present in repo tree — verify it's a template, not real secrets

python/examples/openai/.env.sample

• WARN typescript/.env.sample — .env file present in repo tree — verify it's a template, not real secrets

typescript/.env.sample

Maintenance

_No findings on this axis._

Compatibility

Production sources:

• WARN (meta) — No engines (Node) or python_requires declared — cross-client compatibility unverified

Documentation

Production sources:

• WARN (meta) — No SECURITY.md — no disclosure channel for vulnerabilities

missing

Methodology

SkillAudit v0.2 clones the repo at the provided ref (default: default branch, HEAD) into an ephemeral sandbox, runs six static checks over .js/.ts/.py sources, queries the GitHub API for maintenance signals, and runs an LLM-assisted prompt-injection red-team over the MCP tool surface. Each axis is scored against the rubric at .

The prompt-injection axis extracts each server.tool(...) / @app.tool registration + the first ~60 lines of handler body, hands them to Claude Haiku 4.5 with a red-team system prompt, and asks for structured findings on untrusted-content flow into tool responses. One API call per scan, bounded at ~15K input tokens.

How to improve this grade

• Security — static: validate tool-input URLs against an allowlist before fetch/axios calls; use execFile with argv arrays instead of exec with template strings; never pass untrusted strings to subprocess with shell=True.
• Security — prompt injection: never return fetched web-page / file / email content verbatim in a tool response. Wrap with a framing marker (e.g., <untrusted-content>...</untrusted-content>), summarize rather than inline, and never let untrusted content share a turn with credentials or other tool output.
• Credentials findings: redact env-var reads before log lines and error messages; treat any string that ends up in a tool response as public.
• Maintenance: if the repo is inactive, document the maintenance model — "MCP tool, no breaking changes expected" is a legitimate signal.
• Docs: add a README install + usage section with a copy-pasteable command; add a SECURITY.md with a disclosure channel.

_Report generated by skillaudit.dev_