guide-recap
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from 'CHANGELOG.md' to generate social media drafts, creating a surface where instructions embedded in the file could potentially influence the agent's actions.
- Ingestion points: The skill reads the project's 'CHANGELOG.md' file during Step 2 of the workflow to extract version entries.
- Boundary markers: The instructions do not define specific delimiters or unique markers to isolate the untrusted changelog content from the skill's core instructions.
- Capability inventory: The skill has access to file reading and can use the Bash tool to write outputs to the '[project-docs]/social-posts/' directory.
- Sanitization: While the skill includes scoring and transformation rules in its workflow, it lacks specific sanitization logic to detect or neutralize prompt injection attempts within the parsed entries.
Audit Metadata