deal-with-security-advisory
Handle confidential GitHub Security Advisory response for Paperclip. Use when coordinating advisory triage, private-fork fixes, CVE/publication steps, and immediate security releases.
72
88%
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 workflow reads outsider-authored free text from a GitHub Security Advisory (via `gh api repos/paperclipai/paperclip/security-advisories/{{ghsaId}}`), which is published/associated user-submitted content and is then ingested into the agent context for processing (e.g., `description`, `vulnerabilities`).
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 skill issues GitHub API calls that create a private fork and return a clone URL (e.g., repos/paperclipai/paperclip/security-advisories/{{ghsaId}}/forks), which the workflow then git-clones and runs locally, meaning runtime-fetched repository code can be executed.
- Repository
- paperclipai/paperclip
- Commit
81f47e7
- 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.