endor-oss-request
Trigger ingestion and analysis of a specific open source package version via an Endor Labs OSS dependency request. Use when the user says "trigger OSS dependency request", "request ingestion of <pkg>", "ingest this package", "add this OSS version to Endor", or wants Endor Labs to analyze a package version that isn't yet in the platform. Do NOT use for scanning local code (/endor-scan) or checking an already-ingested package (/endor-check).
Security
1 medium severity finding. This skill can be installed but you should review these findings before use.
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
Third-party content exposure detected (high risk: 0.80). The skill's Step 2 explicitly fetches POM files from public Maven repositories (e.g., https://repo1.maven.org/... and https://maven.artifacts.atlassian.com/...) and parses the POM's <scm> block (third-party, user-published content) to determine the repository clone URL and platform_source, which the agent then uses to construct and send ingestion requests—meeting all criteria for exposure to untrusted external content that can influence actions.
- Repository
- endorlabs/skills-ideas
- Commit
344e7ff
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.