platform-apex-logs-debug

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Salesforce CLI (sf), jq, and ripgrep (rg) to manage and parse debug logs. Commands such as sf apex get log and sf apex tail log are used to retrieve transaction data. These are standard developer tools and their use is consistent with the skill's purpose for the forcedotcom vendor.
  • [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. This represents a potential attack surface for indirect prompt injection where logs could contain instructions to bias the agent's recommendations. However, the risk is minimal as the skill is intended for use in a developer workflow where suggestions are manually reviewed before implementation.
  • Ingestion points: Salesforce .log files retrieved via CLI tools (referenced in SKILL.md and references/cli-commands.md).
  • Boundary markers: Not explicitly defined in the prompts for log processing.
  • Capability inventory: Shell command execution via sf CLI and suggestion of Apex code fixes via integration with platform-apex-generate.
  • Sanitization: None specified for the content of the logs being analyzed.
  • [EXTERNAL_DOWNLOADS]: The documentation references the 'Apex Log Analyzer' VS Code extension (FinancialForce.lana). This is a well-known, trusted community tool in the Salesforce developer ecosystem used for visual log analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 06:22 AM