tdg-personal/search-first
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.
47
59%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill's workflow and Full Mode agent prompt explicitly direct the researcher agent to search and ingest content from public sources like npm/PyPI and GitHub (see "Search: npm/PyPI, MCP servers, Claude Code skills, GitHub" in SKILL.md), which are untrusted, user-generated third-party sites that the agent will read and use to make adoption/implementation decisions.
Where we found it
npmjs.com
domain · 8 sites
The plugin instructs the agent to search npm (npmjs.com) for packages, reading untrusted user-generated package descriptions, READMEs, and metadata that could contain prompt injection.
pypi.org
domain · 5 sites
The plugin instructs the agent to search PyPI (pypi.org) for Python packages, reading untrusted user-generated package descriptions and metadata that could contain prompt injection.
SKILL.md
30
│ │ PyPI │
SKILL.md
65
1. Is this a common problem? → Search npm/PyPI
SKILL.md
80
Search: npm/PyPI, MCP servers, Claude Code skills, GitHub
SKILL.md
123
- Cycle 1: Broad search (npm, PyPI, MCP)
SKILL.md
141
Search: npm "http client retry", PyPI "httpx retry"
github.com
domain · 3 sites
The plugin instructs the agent to search GitHub for implementations and templates, reading untrusted user-generated repository content that could contain prompt injection.
SKILL.md
29
│ │ GitHub / │
SKILL.md
68
4. Is there a GitHub implementation/template? → Run GitHub code search for maintained OSS before writing net-new code
SKILL.md
80
Search: npm/PyPI, MCP servers, Claude Code skills, GitHub
- Audited
- Security analysis