social-media-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external social media content (Instagram and Facebook signals) which serves as an untrusted input vector. Malicious instructions embedded in social media posts could attempt to manipulate agent behavior.
- Ingestion points: Social media content signals and source evidence (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to treat external content as data-only are present.
- Capability inventory: The skill utilizes shell command execution via the
postplusCLI (SKILL.md). - Sanitization: No sanitization or validation routines for external content are defined.
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands using the vendor's own CLI utility to perform tasks and confirm quotes.
- Evidence:
postplus quote confirm --json --challenge-file <challenge.json>and references to owned CLI commands (SKILL.md).
Audit Metadata