tessl-leo/tessl-skill-review-ci
Implements Tessl skill review CI/CD pipelines through an interactive, configuration-first wizard. Supports GitHub Actions, Jenkins, Azure DevOps, and CircleCI.
72
90%
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.
2 low severity findings. 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 pipelines explicitly detect and run "tessl skill review --json <path>" on changed SKILL.md files from pull requests (see "Core Review Logic" in SKILL.md and the GitHub/Azure/CircleCI workflow templates) — meaning it ingests untrusted, user-contributed markdown from public forks/PRs and uses the review output to block builds, post PR comments, and update cache, so third-party content can materially influence actions.
Where we found it
user-contributed SKILL.md files from pull requests / untrusted forks
content-type · 5 sites
SKILL.md's Core Review Logic (lines 38-42) explicitly describes detecting changed SKILL.md files from PR diffs (including untrusted forks, line 53), running `tessl skill review --json <path>` on them, and using the output to block builds and post PR comments — ingesting third-party content that can materially influence CI actions.
SKILL.md
38
1. **Detect** changed `SKILL.md` files (PR diff or full scan)
SKILL.md
39
2. **Review** each with `tessl skill review --json <path>`
SKILL.md
42
5. **Report** results as PR comments with score diff indicators (🔺 🔻 ➡️)
SKILL.md
53
- Accepts external contributions from untrusted forks
SKILL.md
55
- Review pipeline runs in untrusted context, comment pipeline runs with secrets
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The CI templates install and run a third‑party CLI at runtime via "npm install -g @tessl/cli" (fetched from the npm registry, e.g. https://registry.npmjs.org or https://www.npmjs.com/package/@tessl/cli), which downloads and executes remote code that the skill depends on.
- Audited
- Security analysis