review-prose-fix
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell scripts (
check-suppressions.sh) and use thecatcommand to read file contents. These operations are performed using local paths (.claude/skills/fix-prose/scripts/) and are necessary for the skill's primary function of analyzing repository changes. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze the content of target files to provide a verdict on prose fixes. This creates a vulnerability surface where malicious instructions embedded in the reviewed document could attempt to influence the agent's behavior.
- Ingestion points: The skill reads the target file using
catand processes output from a diff script. - Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the ingested text.
- Capability inventory: The agent has the ability to execute shell scripts and read local files.
- Sanitization: No specific sanitization or filtering of the document content is performed before analysis.
Audit Metadata