Fda Guideline Search
v0.1.0Search FDA industry guidelines by therapeutic area or topic. Trigger when user requests FDA guidance documents, regulatory guidelines, or asks about FDA requ...
⭐ 0· 99·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description describe searching FDA guidance by therapeutic area. The code and documentation implement network search/scraping, local PDF caching, and content search — all consistent with that purpose. No unrelated credentials, binaries, or platform access are requested.
Instruction Scope
SKILL.md instructs running the included Python script which performs HTTP requests and writes cached PDFs to references/cache/. These actions are within scope. Two small caveats: (1) the code uses regex-based HTML parsing (fragile but expected for a simple tool) and (2) the docs recommend respecting robots.txt and rate limits, but I did not find explicit robots.txt checking implemented in the visible code. The script does implement a 6-second sleep per request (10 req/min rate).
Install Mechanism
No install spec — instruction-only with a bundled Python script. No external packages are required per SKILL.md and the script uses only Python standard library; therefore nothing is downloaded or installed during skill activation.
Credentials
The skill requires no environment variables, keys, or config paths. The network and filesystem access it uses (HTTP GETs to FDA/ICH and writing to a local cache directory under the skill workspace) are proportionate to a guideline-search tool.
Persistence & Privilege
always is false and the skill does not request elevated or platform-wide privileges. It writes to its own workspace cache (references/cache/) and does not appear to modify other skills or system configuration.
Assessment
This skill is coherent but it runs network requests and writes files. Before running: (1) review the full script (especially any parts after the truncated portion) to confirm downloads are only to the skill workspace and there are no hidden endpoints; (2) run it in a sandboxed environment or container if possible; (3) ensure your environment allows outbound HTTP to fda.gov and database.ich.org and that your organization permits scraping those sites; (4) be aware the scraper uses regex HTML parsing (fragile) and may break if site layout changes; and (5) confirm robots.txt and site terms are respected — the docs say they will be, but I did not see an explicit robots.txt check in the visible code.Like a lobster shell, security has layers — review code before you run it.
latestvk971yk1e9c629ty2v7tgxz1a89838wej
License
MIT-0
Free to use, modify, and redistribute. No attribution required.