The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze Salesforce debug logs (.log files), which are external data sources that could be influenced by an attacker.
Ingestion points: The skill retrieves logs using sf apex get log and sf apex tail log commands as documented in SKILL.md and references/cli-commands.md.
Boundary markers: There are no explicit delimiters or instructions to the AI to ignore instructions embedded within the logs.
Capability inventory: The skill has the capability to execute sf CLI commands, including data deletion (sf data delete record) and creation (sf data create record), as documented in references/cli-commands.md.
Sanitization: There is no evidence of sanitization or validation of the log content before it is processed by the AI.
[COMMAND_EXECUTION]: The skill relies on executing Salesforce CLI commands (sf) to interact with the environment. While these are legitimate tools for the task, the agent has the capability to perform actions like deleting records or modifying configuration, which requires careful oversight.

sf-debug