ig-hashtag-strategist
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated content to determine hashtag recommendations, which introduces a vulnerability to indirect prompt injection.
- Ingestion points: The skill ingests untrusted text including captions, carousel topics, and Reel subjects as defined in Step 1 of
SKILL.md. - Boundary markers: There are no instructions or delimiters provided to the agent to separate the user-provided data from the operational instructions, potentially allowing a malicious input to influence the agent's behavior.
- Capability inventory: The skill is limited to providing text-based recommendations and does not possess capabilities for network operations, file system modification, or command execution.
- Sanitization: No input filtering, validation, or sanitization techniques are mentioned in the skill files.
Audit Metadata