bluesky
Read from and post to Bluesky social network using the AT Protocol. Use this skill when the user wants to interact with Bluesky including posting text/images/links, replying to posts, reading their timeline, searching posts, viewing profiles, following/unfollowing users, checking notifications, or viewing reply threads. All scripts use PEP 723 inline metadata for dependencies and run via `uv run`. Requires BLUESKY_HANDLE and BLUESKY_PASSWORD environment variables.
87
82%
Does it follow best practices?
Impact
94%
1.44xAverage score across 3 eval scenarios
Critical
Do not install without reviewing
Security
2 findings — 1 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
Suspicious download URL detected (high risk: 0.90). The set includes a direct link to an install.sh (https://astral.sh/uv/install.sh) and the skill explicitly instructs piping a remote shell script to sh (curl ... | sh), a common high-risk vector for distributing malware, while the other URLs are documentation or social links and are not themselves downloads.
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: 0.90). The skill's scripts explicitly fetch and ingest public, user-generated Bluesky content (via the bsky API/web URLs) — see scripts/read_timeline.py, scripts/search.py, scripts/replies.py, scripts/profile.py and scripts/notifications.py which retrieve posts, profiles, threads and notifications from bsky.app/public.api.bsky.app — so untrusted third‑party content is read and used as part of the agent's workflow (e.g., resolving threads, building reply references, displaying and acting on profile/follow state), enabling potential indirect prompt injection.
- Repository
- fpl9000/ai-skills
- Commit
3f74412
- 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.