social-selling-content-generator-skill
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data such as target audience descriptions and solution details to generate social media posts. This creates a surface for indirect prompt injection where malicious instructions embedded in the input could influence the agent's behavior during content generation.\n
- Ingestion points: User-provided inputs for target audience, solution, and goals defined in the quick start and workflow sections of SKILL.md.\n
- Boundary markers: The skill does not employ delimiters or specific instructions to ignore potential commands within the user data.\n
- Capability inventory: The agent is tasked with writing a JSON outcome to the local file system in SKILL.md.\n
- Sanitization: No explicit validation or filtering of external content is mentioned.\n- [COMMAND_EXECUTION]: The workflow specifies a step to write a JSON object containing session metrics to a local path (~/.claude/skill-analytics/last-outcome-social-selling-content-generator.json). This requires the agent to have file system write permissions and follow instructions to modify the local environment.
Audit Metadata