The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, untrusted data from Salesforce Apex logs, creating a surface for indirect prompt injection attacks.
Ingestion points: The agent is directed to read log content using sf electivus log read in SKILL.md and to perform local searches on log files using rg (ripgrep) as described in references/local-search.md.
Boundary markers: The instructions lack specific guidance on using delimiters or explicitly ignoring instructions that may be embedded within the log data during triage.
Capability inventory: The skill environment provides the agent with significant capabilities, including the ability to install plugins via sf plugins install, delete logs with sf electivus log delete, and modify Salesforce org state through trace flag and debug level management.
Sanitization: There are no explicit instructions for sanitizing or escaping the content of log files before it is processed by the agent.
[COMMAND_EXECUTION]: The skill operates by executing several shell commands via the Salesforce CLI (sf) and ripgrep (rg). These commands are used for core functionality such as synchronizing logs (log sync), querying the Tooling API (tooling query), and searching through the local log corpus. While legitimate for the skill's purpose, they represent a significant execution surface.
[EXTERNAL_DOWNLOADS]: The skill documentation includes instructions for downloading and installing the @electivus/plugin-electivus plugin and updating the skill itself using npx. These operations involve fetching and executing code from the NPM registry to maintain the toolset.

apex-log-viewer-cli