developer-advocacy

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions in SKILL.md direct the agent to read audience information from a local file located at .agents/developer-audience-context.md. This represents a potential surface for indirect prompt injection if the content of that file is influenced by untrusted data.
  • Ingestion points: SKILL.md (reading .agents/developer-audience-context.md).
  • Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded commands within the ingested context file.
  • Capability inventory: None detected; the skill provides textual templates and strategic advice with no ability to execute shell commands, write to the file system, or perform network operations.
  • Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The skill provides links to official websites for well-known developer advocacy tools, including Octolens, Cal.com, StreamYard, Descript, and Typefully. These are informational references to legitimate services and do not involve automated downloads or execution of code.
  • [NO_CODE]: The skill consists entirely of Markdown-based instructions and templates. It contains no scripts, binaries, or automated code execution patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:36 PM