Security audit
Security checks for vulnerabilities and agentic risk
This is a project-specific development guide for a Bilibili Rust CLI, with sensitive account features documented but no hidden execution or unsafe install behavior in the skill itself.
Install only if you are working on the bili-rs Bilibili CLI. Treat commands that read history or change account state as sensitive, and require explicit user intent before implementing or running posting, deletion, follow, like, coin, or credential-related flows.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
- `Read` — requires SESSDATA
- `Write` — requires SESSDATA + bili_jct
Credential file: `~/.bilibili-cli/credential.json` (0o600, 7-day TTL)
## WBI Signature
The description says to use the skill when implementing features, fixing bugs, or extending the codebase, and lists broad task categories like adding CLI commands or handling authentication. For a markdown skill file, this is an ambiguous activation scope because it does not define explicit trigger phrases, exclusions, or negative examples to distinguish when the skill should or should not activate.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
# bili-rs Development Skill
Rust rewrite of [bilibili-cli](https://github.com/jackwener/bilibili-cli). Single binary, no runtime deps. Full feature parity with the Python original.
## Architecture (strict layering)
The document explicitly enumerates authenticated write/destructive API operations such as posting dynamics, deleting dynamics, modifying relations, and liking/coining videos, but provides no safety notes about account-impacting behavior, confirmation requirements, or the need to avoid invoking such endpoints automatically. In an agent skill context, this increases the chance that an automated coding or execution workflow will implement or trigger state-changing actions without sufficient user awareness or guardrails.
This markdown file documents bili login as QR scan → save credential, which indicates persistent storage of authentication material. The description does not include any warning about where credentials are stored, their persistence, or the privacy/security implications of saving them locally.
bili dynamic-post creates account content, which can affect the user's public profile or followers. The reference states the syntax but does not warn that this is a write action with user-visible consequences, unlike neighboring destructive commands that explicitly mention confirmation behavior.
The markdown advertises bili history as returning watch history, which is user-sensitive behavioral data. There is no accompanying warning that invoking this command may reveal private account activity or should be used cautiously in shared/logged environments.